© 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. 95273
    Prev
    Next
    INDEX
    Explanations

    meet

    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
    .si
    -0.30
     Himself
    -0.26
    aver
    -0.26
    åĵij
    -0.26
    ért
    -0.26
    åľ¨æĪij
    -0.26
    cow
    -0.26
    å°ıå¾®
    -0.26
     EO
    -0.25
    .Mapper
    -0.25
    POSITIVE LOGITS
     the
    0.38
     your
    0.35
    æħİ
    0.31
     those
    0.30
     society
    0.29
     recurring
    0.28
     their
    0.28
     immediate
    0.27
     escalating
    0.26
     its
    0.26
    Activations Density 0.888%

    No Known Activations