© 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. 87454
    Prev
    Next
    INDEX
    Explanations

    at

    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
     Lives
    -0.28
     Deck
    -0.25
    uche
    -0.25
     Transcript
    -0.25
    ijn
    -0.25
    GPL
    -0.24
    轻轻
    -0.24
    ä¸ĢæŃ¥æŃ¥
    -0.24
    ewise
    -0.24
    æľ¬çĿĢ
    -0.24
    POSITIVE LOGITS
    cuts
    0.28
    mdb
    0.26
     unlucky
    0.26
    æ¢ĵ
    0.25
     pervasive
    0.25
    Ùĥب
    0.24
     perv
    0.24
    ãĤĤãģªãģĦ
    0.24
    å¦Ĥæŀľæ²¡æľī
    0.24
     invasive
    0.24
    Activations Density 0.006%

    No Known Activations