© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 89010
    Prev
    Next
    INDEX
    Explanations

    fixing, preventing, or stopping

    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
    Negative Logits
    çŃīä¸Ģæī¹
    -0.27
     Feedback
    -0.24
     discussing
    -0.23
    è¿Ļæīįæĺ¯
    -0.23
     resid
    -0.23
    è£
    -0.22
    .cls
    -0.22
     closed
    -0.22
    ÑıÑī
    -0.22
     feedback
    -0.22
    POSITIVE LOGITS
    èĻı
    0.27
    block
    0.26
    hawk
    0.25
     kep
    0.24
    åĽŀæĿ¥
    0.24
    è¿ĺæĺ¯å¾Ī
    0.24
    åĩºåħ¥
    0.24
    åħļåĴĮåĽ½å®¶
    0.23
    åĬŁè¯¾
    0.23
    ãĤ·ãĥ§ãĥ¼
    0.23
    Activations Density 0.006%

    No Known Activations