© 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. 9-TRANSCODER-HP
    7. 30437
    Prev
    Next
    INDEX
    Explanations

    sm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    hq
    -0.34
    ľ
    -0.26
     '~/
    -0.25
     succ
    -0.25
    泺
    -0.25
     Kum
    -0.24
    stime
    -0.24
    orge
    -0.24
    (QL
    -0.24
    лом
    -0.24
    POSITIVE LOGITS
    DataContract
    0.26
    åıªè¦ģä½ł
    0.26
     removeObject
    0.25
    RAP
    0.25
     knees
    0.25
     entert
    0.25
    æ¦ķ
    0.24
    çľĭ好
    0.24
    è¿IJæ°Ķ
    0.24
    åİŁåīĩ
    0.24
    Activations Density 1.074%

    No Known Activations