© 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. 32-TRANSCODER-HP
    7. 42671
    Prev
    Next
    INDEX
    Explanations

    gene

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DIC
    -0.27
    å¼
    -0.25
    rem
    -0.25
    resenter
    -0.24
    å®ĩ
    -0.24
    [msg
    -0.24
    LastError
    -0.24
    ä¸Ģæīĭ
    -0.24
    allah
    -0.24
    =msg
    -0.24
    POSITIVE LOGITS
     gene
    0.31
     Gene
    0.29
    Gene
    0.29
    unce
    0.29
    /Sub
    0.26
    POR
    0.26
    IJèĹı
    0.26
    ude
    0.25
    -interface
    0.25
     levels
    0.25
    Activations Density 0.004%

    No Known Activations