© 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. 57342
    Prev
    Next
    INDEX
    Explanations

    reck

    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
    odic
    -0.29
    ctic
    -0.26
    azers
    -0.24
    å®ŀ
    -0.24
    ç§Ģ
    -0.24
     pale
    -0.24
     strategy
    -0.24
     heiÃŁ
    -0.23
    åĭ¾
    -0.23
    otti
    -0.23
    POSITIVE LOGITS
    ened
    0.37
    led
    0.34
    ening
    0.33
    lemen
    0.32
    le
    0.29
    eln
    0.29
    ified
    0.28
    lef
    0.28
    itude
    0.28
    ely
    0.27
    Activations Density 0.024%

    No Known Activations