© 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. 98630
    Prev
    Next
    INDEX
    Explanations

    July Fourth

    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
    imb
    -0.26
     mang
    -0.25
    aves
    -0.25
     Nr
    -0.25
     Maiden
    -0.25
    éal
    -0.25
    ware
    -0.24
    he
    -0.24
    adv
    -0.24
    (s
    -0.24
    POSITIVE LOGITS
    éľĢè¦ģçĶ¨
    0.27
    éĹ´éļĻ
    0.25
     {{↵
    0.25
    åľ¨ç¾İåĽ½
    0.25
    SSION
    0.25
    gL
    0.24
    imity
    0.24
    /lg
    0.23
     docking
    0.23
    дон
    0.23
    Activations Density 0.005%

    No Known Activations