© 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. 32-TRANSCODER-HP
    7. 41170
    Prev
    Next
    INDEX
    Explanations

    scientific names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    á»ģm
    -0.28
     anale
    -0.28
    iore
    -0.27
     lim
    -0.26
    Ĥ¤
    -0.26
    =sys
    -0.26
    æ°Ļ
    -0.26
    éĻĦ件
    -0.26
     <![
    -0.26
     cis
    -0.25
    POSITIVE LOGITS
     Cry
    0.32
    ESCO
    0.31
    onas
    0.29
    REEN
    0.29
    æµĨ
    0.28
    éļ¼
    0.25
    Buzz
    0.25
    rink
    0.24
     Exit
    0.24
    å¾Ĺå¤ļ
    0.24
    Activations Density 0.007%

    No Known Activations