© 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. 35-TRANSCODER-HP
    7. 39222
    Prev
    Next
    INDEX
    Explanations

    single digit numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.40
     in
    -0.35
     for
    -0.34
     the
    -0.33
     to
    -0.33
     as
    -0.30
     on
    -0.30
     that
    -0.29
     with
    -0.29
     at
    -0.28
    POSITIVE LOGITS
    2
    0.72
    1
    0.69
    3
    0.69
    5
    0.68
    6
    0.67
    4
    0.66
    7
    0.66
    8
    0.66
    9
    0.66
    0
    0.49
    Activations Density 86.804%

    No Known Activations