© 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. 20-TRANSCODER-HP
    7. 130995
    Prev
    Next
    INDEX
    Explanations

    he

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    sav
    -0.26
     NodeType
    -0.26
    绯
    -0.25
     sourceMappingURL
    -0.25
    sic
    -0.24
    å¤ĸè´¸
    -0.24
     apprent
    -0.24
    碧
    -0.24
    çĶŁ
    -0.23
    thood
    -0.23
    POSITIVE LOGITS
    èĪ¶
    0.29
    ä¸įä½ı
    0.28
    éĻ·éĺ±
    0.26
    iano
    0.25
     exceptions
    0.24
    IZER
    0.24
    许
    0.24
     Elder
    0.24
    ish
    0.23
    icate
    0.23
    Activations Density 27.969%

    No Known Activations