© 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. 27-TRANSCODER-HP
    7. 58254
    Prev
    Next
    INDEX
    Explanations

    wait

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĽı
    -0.28
    _EXTENDED
    -0.24
    ichern
    -0.24
    å¦Ĥå®ŀ
    -0.24
    abeth
    -0.23
     ce
    -0.23
     swore
    -0.23
    åķĨåĬ¡
    -0.23
    Defined
    -0.23
     Wr
    -0.23
    POSITIVE LOGITS
    人士
    0.26
    otec
    0.26
    maids
    0.25
    éĤ£æ®µ
    0.25
    aura
    0.25
    pur
    0.25
    HandlerContext
    0.25
    å®ģåİ¿
    0.24
     INCIDENT
    0.24
    yling
    0.24
    Activations Density 0.004%

    No Known Activations