© 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. 97867
    Prev
    Next
    INDEX
    Explanations

    Bishop

    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
    并ä¸įæĦıåij³
    -0.27
    tsy
    -0.26
    isa
    -0.26
    ounc
    -0.24
    好æ¶Īæģ¯
    -0.24
    endors
    -0.24
     rewritten
    -0.23
    aser
    -0.23
     Duchess
    -0.23
    ters
    -0.23
    POSITIVE LOGITS
     tent
    0.27
    erset
    0.27
    node
    0.27
    驳
    0.27
    ering
    0.26
    uring
    0.25
     bay
    0.25
    ley
    0.24
    coli
    0.24
    erver
    0.24
    Activations Density 0.083%

    No Known Activations