© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96875
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    Negative Logits
    å·¥ä½ľç»ıéªĮ
    -0.34
    Fuel
    -0.27
    adt
    -0.27
    cka
    -0.26
     experiences
    -0.25
    rze
    -0.25
    EAR
    -0.25
    imore
    -0.25
    cart
    -0.25
    çĩĥ
    -0.25
    POSITIVE LOGITS
     subconscious
    0.28
    éļĶå£ģ
    0.26
    pii
    0.25
    ä¼ĺ
    0.25
    .diag
    0.25
    æŀľæĸŃ
    0.24
    vn
    0.24
     invocation
    0.24
    insky
    0.24
    anch
    0.24
    Activations Density 0.102%

    No Known Activations