© 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. 56407
    Prev
    Next
    INDEX
    Explanations

    Amazon

    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
    Negative Logits
    eton
    -0.27
    unger
    -0.27
    éĵ¶è¡Įä¸ļ
    -0.26
    ãģĻãĤĭãģĵãģ¨ãģ¯
    -0.26
    -guard
    -0.26
     UNIVERS
    -0.25
    bestos
    -0.25
    -indent
    -0.24
    çĶ¨äºĨ
    -0.24
     Wal
    -0.24
    POSITIVE LOGITS
     Exist
    0.29
    rik
    0.28
     predomin
    0.28
    Exist
    0.27
     exist
    0.26
     lur
    0.26
     counts
    0.24
    ä½ķå¤Ħ
    0.24
    份é¢Ŀ
    0.24
     most
    0.24
    Activations Density 0.005%

    No Known Activations