© 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. 23373
    Prev
    Next
    INDEX
    Explanations

    Scientific research

    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
    ovation
    -0.27
    åĵĪä½Ľ
    -0.25
    usercontent
    -0.24
    .Syntax
    -0.24
     déc
    -0.24
    redient
    -0.24
    ReturnType
    -0.24
    æ¯Ķè¾ĥ大
    -0.24
    istles
    -0.23
    EditMode
    -0.23
    POSITIVE LOGITS
     implies
    0.50
    æĦıåij³çĿĢ
    0.49
    å°±æĦıåij³çĿĢ
    0.45
    æīįèĥ½
    0.43
    åĪĻ
    0.42
     ensures
    0.42
     means
    0.40
    å°±èĥ½
    0.38
    å°±åı¯ä»¥
    0.37
     imply
    0.36
    Activations Density 0.007%

    No Known Activations