© 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. 40378
    Prev
    Next
    INDEX
    Explanations

    numerical data and code

    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
     č↵ č↵
    -0.21
     ç±
    -0.19
    <P
    -0.19
    åĪĺ
    -0.19
    <R
    -0.19
    <B
    -0.19
     åĴĮ
    -0.18
    <D
    -0.18
    <M
    -0.18
    .getM
    -0.18
    POSITIVE LOGITS
    eo
    0.21
    g
    0.21
    Tpl
    0.20
    y
    0.20
    o
    0.20
    Fs
    0.19
    ongyang
    0.19
    eur
    0.19
    fds
    0.18
    gw
    0.18
    Activations Density 12.933%

    No Known Activations