© 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. 8285
    Prev
    Next
    INDEX
    Explanations

    using

    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
    eti
    -0.25
    ÃŃsticas
    -0.25
    obia
    -0.25
     equ
    -0.24
    grown
    -0.24
    æĺı
    -0.24
    +',
    -0.24
     ever
    -0.23
    çĺ¤
    -0.23
    OrDefault
    -0.23
    POSITIVE LOGITS
     separately
    0.31
     Separate
    0.30
     separate
    0.29
     expend
    0.28
     disposable
    0.28
     seperate
    0.26
     murdered
    0.26
    SEG
    0.26
    便åĪ©
    0.26
    件
    0.25
    Activations Density 0.000%

    No Known Activations