© 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. 19-TRANSCODER-HP
    7. 8288
    Prev
    Next
    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fried
    -0.28
    ULK
    -0.28
    é²Ī
    -0.27
    INET
    -0.25
    ologue
    -0.25
    éĶ¤
    -0.24
     protestors
    -0.24
    gé
    -0.24
    éĩĮæĸ¯
    -0.24
    aux
    -0.24
    POSITIVE LOGITS
     Jackson
    0.26
    _CN
    0.26
    çĻ»éĻĨ
    0.25
    天ä¸ĭ
    0.25
    WX
    0.25
    aren
    0.25
     erection
    0.25
     guid
    0.24
    apl
    0.24
    Corn
    0.24
    Activations Density 0.005%

    No Known Activations