© 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. 112466
    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
    丢
    -0.25
    æıĸ
    -0.25
     shy
    -0.24
     den
    -0.24
     szkoÅĤy
    -0.23
    çĵ¶é¢Ī
    -0.23
    CSI
    -0.23
    renc
    -0.23
    ä¹Łå¥½
    -0.23
     ÑįÑĤ
    -0.23
    POSITIVE LOGITS
    );$
    0.25
    yw
    0.25
    pone
    0.25
    ľëł¥
    0.24
    eus
    0.23
    ãĤĭãĤĤãģ®
    0.23
    æĭīæĸ¯
    0.23
    éĥ¨éķ¿
    0.22
    eous
    0.22
    stateParams
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.