© 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. 8874
    Prev
    Next
    INDEX
    Explanations

    Non-English/Code Text

    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
    edis
    -0.32
    _deck
    -0.28
     pools
    -0.28
     pooling
    -0.27
    ×Ļ×Ķ
    -0.26
     NOTIFY
    -0.26
     salads
    -0.25
    atrix
    -0.25
    ialis
    -0.25
    lessness
    -0.25
    POSITIVE LOGITS
     whisk
    0.28
    æľ¬ç«Ļ
    0.27
    å¡ij
    0.26
    æ»ļ
    0.26
    çļĦåľŁåľ°
    0.25
    -wh
    0.25
     Spears
    0.24
    åľŁåľ°
    0.24
    èĥ½éĩı
    0.24
     thẩm
    0.24
    Activations Density 0.002%

    No Known Activations