© 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. 23-TRANSCODER-HP
    7. 23400
    Prev
    Next
    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     others
    -0.29
     worth
    -0.28
     Others
    -0.27
     theirs
    -0.27
    大çģ«
    -0.27
    åħ¥éĢī
    -0.26
    Others
    -0.25
    éĿ¢ç§¯çº¦
    -0.25
    Https
    -0.25
    çģ«çģ¾
    -0.25
    POSITIVE LOGITS
    agner
    0.26
     kron
    0.25
     antis
    0.25
    Notifier
    0.25
    anguard
    0.25
    less
    0.25
    unas
    0.25
    å°¼æĸ¯
    0.25
    宽
    0.24
     subject
    0.24
    Activations Density 0.073%

    No Known Activations