© 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. 9-TRANSCODER-HP
    7. 30107
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     å¤
    -0.28
    泡
    -0.27
    家ä½ı
    -0.27
    åĪĨæĺİ
    -0.26
    Mob
    -0.25
    ä¼ij
    -0.25
    纵åIJij
    -0.25
    åĵªç§į
    -0.25
     reli
    -0.24
    /m
    -0.24
    POSITIVE LOGITS
    å¼¼
    0.27
    itta
    0.26
    ãĤĪãģĨãģ«ãģªãģ£ãģŁ
    0.25
    cÃŃ
    0.25
    rather
    0.24
     squir
    0.24
    ãģłãģijãģ©
    0.24
    ãģĭãģ£ãģŁ
    0.24
    alars
    0.24
    klär
    0.24
    Activations Density 1.250%

    No Known Activations