© 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. 87309
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    ä»Ģä¹Īåij¢
    -0.27
    á»Į
    -0.23
    绾
    -0.23
    姹
    -0.23
    éĿ¢çĽ®
    -0.23
     stands
    -0.23
    idental
    -0.23
    IFO
    -0.23
    éĿ¢åIJij
    -0.23
    åİĨæŶ
    -0.22
    POSITIVE LOGITS
    uder
    0.26
    awl
    0.24
    elles
    0.24
    swith
    0.23
    amped
    0.23
    ç©·
    0.23
    tte
    0.23
    æѦ
    0.23
    reject
    0.23
     cup
    0.23
    Activations Density 0.008%

    No Known Activations