© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56756
    Prev
    Next
    INDEX
    Explanations

    technical context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æī©å±ķ
    -1.41
     extension
    -1.34
     extend
    -1.32
    延伸
    -1.25
     extending
    -1.22
     extends
    -1.20
     extended
    -1.20
     extensions
    -1.19
    extend
    -1.17
     Extension
    -1.17
    POSITIVE LOGITS
    inium
    0.27
    åĬłæ²¹
    0.26
     ÙĪÙĥ
    0.25
    /****************************************************************************↵
    0.24
    /reset
    0.23
     crunch
    0.23
    _bio
    0.23
    èļĮ
    0.23
     Andrews
    0.22
    isel
    0.22
    Activations Density 0.001%

    No Known Activations