© 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. 39770
    Prev
    Next
    INDEX
    Explanations

    k

    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
     facult
    -0.27
    ç»
    -0.27
     revolving
    -0.25
    æľī幸
    -0.24
    åĴĮè°IJ
    -0.24
     Sá»Ń
    -0.24
    ov
    -0.24
    çĨŁçŁ¥
    -0.24
    æ°¸ä¸į
    -0.24
    ä¸īåĨľ
    -0.23
    POSITIVE LOGITS
    idle
    0.31
    ipline
    0.30
    aticon
    0.29
    letic
    0.27
    ionage
    0.27
    ecycle
    0.27
    ifecycle
    0.27
    eeee
    0.26
    izona
    0.26
     pull
    0.26
    Activations Density 7.715%

    No Known Activations