© 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. 22-TRANSCODER-HP
    7. 131037
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    airo
    -0.27
    IPHER
    -0.25
     Já
    -0.24
    ofday
    -0.24
    å¦Ĥæŀľè¯´
    -0.23
    è¥ģ
    -0.23
    ocal
    -0.23
    JsonObject
    -0.23
    çĿ
    -0.23
    WithPath
    -0.23
    POSITIVE LOGITS
    æģ©
    0.26
     provinc
    0.25
    è±Ĩçĵ£
    0.25
    çİ°åľº
    0.25
     concern
    0.25
    æłĪ
    0.24
    ä¸į大
    0.24
     begged
    0.24
    contact
    0.24
    åıijçİ°èĩªå·±
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.