© 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. 42905
    Prev
    Next
    INDEX
    Explanations

    not

    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
     gel
    -0.27
    ller
    -0.27
    ì²Ń
    -0.26
     branch
    -0.26
    ä¼Łå¤§
    -0.25
     Roo
    -0.25
    çļĦä¼Łå¤§
    -0.25
    äºĨèµ·æĿ¥
    -0.25
    Ro
    -0.25
     clo
    -0.25
    POSITIVE LOGITS
     prove
    0.38
    roduce
    0.30
    anding
    0.29
     proved
    0.28
    prove
    0.27
    INGER
    0.27
     Provide
    0.27
    è¯ģæĺİ
    0.27
     reproduce
    0.27
    inger
    0.27
    Activations Density 0.009%

    No Known Activations