© 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. 96489
    Prev
    Next
    INDEX
    Explanations

    note

    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
     written
    -0.41
     Written
    -0.38
    Written
    -0.32
     wrote
    -0.31
    书éĿ¢
    -0.31
    åĨĻçļĦ
    -0.30
    -written
    -0.30
    åĨĻ
    -0.30
    _written
    -0.29
    åŃĹ
    -0.28
    POSITIVE LOGITS
    inely
    0.31
    ucker
    0.27
    iks
    0.27
    管çIJĨå±Ģ
    0.27
    ARS
    0.27
     baÅŁÄ±na
    0.25
    osen
    0.25
    ads
    0.25
    å°¼åħĭ
    0.24
    allback
    0.24
    Activations Density 0.101%

    No Known Activations