© 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. 18-TRANSCODER-HP
    7. 88477
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľĽ
    -0.29
    ISHED
    -0.27
    cade
    -0.26
    åĿIJ
    -0.26
    ãģ§ãģĻãģĹ
    -0.25
    )\<
    -0.25
    åģľäº§
    -0.24
    踩
    -0.24
    ispens
    -0.24
     Sitting
    -0.24
    POSITIVE LOGITS
    ser
    0.31
    -ser
    0.27
     wir
    0.27
     supposed
    0.26
    imens
    0.25
     firm
    0.25
    sel
    0.24
    fir
    0.24
     theor
    0.24
    pir
    0.24
    Activations Density 26.782%

    No Known Activations