© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96307
    Prev
    Next
    INDEX
    Explanations

    website content and parsing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Season
    -0.42
     season
    -0.41
    Season
    -0.38
     seasons
    -0.38
    åŃ£èĬĤ
    -0.38
     respect
    -0.33
    åŃ£
    -0.33
    _season
    -0.33
    season
    -0.32
     seasonal
    -0.32
    POSITIVE LOGITS
     mid
    0.27
    çŃĸ
    0.26
     ni
    0.26
    SWG
    0.26
     couples
    0.26
     labelText
    0.26
    enthal
    0.25
     Couples
    0.25
     cover
    0.24
     Couldn
    0.24
    Activations Density 0.102%

    No Known Activations