© 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. 112566
    Prev
    Next
    INDEX
    Explanations

    Time periods

    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
    å®Ľ
    -0.29
    icap
    -0.26
    å°ī
    -0.25
    æ£ī
    -0.25
    ossal
    -0.25
    ç¼°
    -0.25
    èıĢ
    -0.25
    amide
    -0.24
     Attached
    -0.24
    ×ķ×IJר
    -0.23
    POSITIVE LOGITS
    erah
    0.28
    æĬ½
    0.26
    âĨ©
    0.26
    ç»ıæµİæįŁå¤±
    0.26
     greed
    0.26
    磨
    0.25
    å¸ĥæľĹ
    0.24
    æµģåIJij
    0.24
    ãĥ©ãĥ³ãĤ¹
    0.24
    [..
    0.24
    Activations Density 0.004%

    No Known Activations