© 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. 87161
    Prev
    Next
    INDEX
    Explanations

    while

    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
     |↵
    -0.29
     sa
    -0.28
     |
    -0.27
    -0.27
    hin
    -0.25
    -0.25
    ↵
    -0.25
     ahead
    -0.24
     chÄĥm
    -0.24
    ')
    -0.24
    POSITIVE LOGITS
    égor
    0.28
    /stdc
    0.28
    IFIED
    0.27
    resse
    0.27
     deflate
    0.26
    è¶Ĭ
    0.26
    ivité
    0.26
    çĶ¨æĿ¥
    0.26
    atile
    0.26
    ographically
    0.26
    Activations Density 0.012%

    No Known Activations