© 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. 58250
    Prev
    Next
    INDEX
    Explanations

    processes and methods

    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
    Maker
    -0.28
    abol
    -0.26
    chner
    -0.26
     taraf
    -0.26
    侦
    -0.24
    å°Ķ
    -0.24
    è¯Ŀ
    -0.24
    åľ¨ä¸Ĭæµ·
    -0.24
    Ñĥ
    -0.24
    åį¡
    -0.24
    POSITIVE LOGITS
    èĭ¥ãģĦ
    0.34
    年轻人
    0.31
     young
    0.30
     individual
    0.28
    çķ°ãģªãĤĭ
    0.28
    æĸ°æĬĢæľ¯
    0.28
    æľªæĪIJå¹´
    0.27
    ç½ijåıĭè¯Ħ论
    0.26
    perienced
    0.26
     einzel
    0.26
    Activations Density 0.059%

    No Known Activations