© 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. 130560
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĭ¿æĿ¥
    -0.28
    -dom
    -0.26
    -calendar
    -0.25
    æīĢåľ¨åľ°
    -0.25
    иÑĤеÑĤ
    -0.24
    fern
    -0.24
    iates
    -0.23
    iator
    -0.23
    åĤ¬çĶŁ
    -0.23
    haps
    -0.23
    POSITIVE LOGITS
     slashing
    0.28
     sed
    0.26
    Hyper
    0.26
    ppers
    0.25
    Ir
    0.23
    对èĩªå·±
    0.23
    pike
    0.23
    è¿Ľè¡Įåħ¨éĿ¢
    0.23
    åĹĵåŃIJ
    0.23
    ä¸ĵ项
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.