© 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. 39421
    Prev
    Next
    INDEX
    Explanations

    a

    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
    nio
    -0.29
    cter
    -0.29
    utow
    -0.28
    gae
    -0.28
    udios
    -0.27
    uncios
    -0.27
    nier
    -0.27
    ging
    -0.27
    nicas
    -0.27
    uib
    -0.27
    POSITIVE LOGITS
    èĩ
    0.27
    çİ·
    0.26
     mafia
    0.25
    Eastern
    0.25
    åĨµ
    0.24
    President
    0.24
     misog
    0.24
     LORD
    0.24
    .E
    0.24
    .DE
    0.24
    Activations Density 17.174%

    No Known Activations