© 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. 33-TRANSCODER-HP
    7. 54491
    Prev
    Next
    INDEX
    Explanations

    titles and royalty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĬµæĬ¼
    -0.26
    pecia
    -0.26
     dou
    -0.26
    anden
    -0.25
    nier
    -0.25
    轨éģĵ
    -0.24
    DEM
    -0.24
    estate
    -0.24
    é¼İ
    -0.24
    æ³ķéĻ¢
    -0.24
    POSITIVE LOGITS
    RULE
    0.42
     RULE
    0.41
    è§ĦåĪĻ
    0.40
     rules
    0.40
    Rule
    0.39
    -rule
    0.36
    rules
    0.35
     Rule
    0.35
     rule
    0.35
    (rule
    0.35
    Activations Density 0.005%

    No Known Activations