© 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. 30-TRANSCODER-HP
    7. 96735
    Prev
    Next
    INDEX
    Explanations

    pro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĥÑģ
    -0.27
    RIX
    -0.27
     reaction
    -0.27
    åīįä»»
    -0.27
    aggio
    -0.26
    uais
    -0.26
    ussy
    -0.26
    ajor
    -0.26
    åįģåĪĨéĩįè¦ģ
    -0.25
    éĥ½éĿŀ常
    -0.25
    POSITIVE LOGITS
    stroke
    0.31
    é©¿
    0.31
     stroke
    0.29
    Stroke
    0.28
    ç»ıæµİ
    0.26
    ff
    0.25
     thuyết
    0.25
    ç²¾ç¥ŀ
    0.25
    kat
    0.25
     lyr
    0.25
    Activations Density 0.024%

    No Known Activations