© 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. 22-TRANSCODER-HP
    7. 111645
    Prev
    Next
    INDEX
    Explanations

    Scientific names/studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    带ä¸Ĭ
    -0.28
    Ãŀ
    -0.25
     nan
    -0.25
    qus
    -0.25
    Hi
    -0.25
    çĶ¨æīĭ
    -0.25
     DO
    -0.25
    full
    -0.25
    æĥ³æĥ³
    -0.25
    thin
    -0.24
    POSITIVE LOGITS
    aternity
    0.27
    angelo
    0.26
     Ã¶ÄŁrenc
    0.25
    inerary
    0.25
    deaux
    0.24
     interrogation
    0.23
     bordel
    0.23
    olio
    0.23
    ITOR
    0.23
    éĢļé£İ
    0.23
    Activations Density 0.043%

    No Known Activations