© 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. 31-TRANSCODER-HP
    7. 19028
    Prev
    Next
    INDEX
    Explanations

    Northern

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trá»Ŀi
    -0.30
    åģļ梦
    -0.28
    controllers
    -0.27
    bens
    -0.27
     quantity
    -0.27
    itude
    -0.25
    çĻ½æ²Ļ
    -0.25
    æı½
    -0.25
    quantity
    -0.25
    åģ»
    -0.24
    POSITIVE LOGITS
    ivol
    0.29
    vester
    0.27
    ropy
    0.25
    ulos
    0.25
     convenience
    0.25
     paras
    0.25
    çīĤ
    0.25
    iego
    0.25
    -abortion
    0.24
    éªĪ
    0.23
    Activations Density 0.145%

    No Known Activations