© 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. 131074
    Prev
    Next
    INDEX
    Explanations

    ose

    np_max-act · gemini-2.0-flash
    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
    çĬ¶
    -0.29
    åĪĢ
    -0.29
    rub
    -0.28
    æłĩè¯Ĩ
    -0.27
    chair
    -0.25
    æł¹æľ¬
    -0.25
    rtle
    -0.24
    åIJĦåįķä½į
    -0.24
    èĦļ
    -0.24
    å½¢å¼ı
    -0.24
    POSITIVE LOGITS
    SENS
    0.28
    FetchRequest
    0.27
     amy
    0.25
    æĿŀ
    0.24
     chù
    0.24
    é²ł
    0.24
    veau
    0.23
    ea
    0.23
    å®£ä¼łçīĩ
    0.23
    assin
    0.23
    Activations Density 0.154%

    No Known Activations