© 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. 95078
    Prev
    Next
    INDEX
    Explanations

    code and aesthetics

    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
    åİ¿éķ¿
    -0.32
    ến
    -0.28
    å¿ĥ头
    -0.27
    æĿ¡çº¦
    -0.26
    inion
    -0.26
    LEMENT
    -0.25
    .intent
    -0.25
    .timeout
    -0.24
     perman
    -0.24
     contracting
    -0.24
    POSITIVE LOGITS
    rop
    0.29
    积æŀģ
    0.28
    pecific
    0.28
    æ¯Ķ
    0.27
    omatic
    0.27
    Ill
    0.27
    è½»
    0.27
    æ´İ
    0.26
     Style
    0.26
    rance
    0.26
    Activations Density 0.009%

    No Known Activations