© 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. 87694
    Prev
    Next
    INDEX
    Explanations

    computer-related

    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
    ä¼ĺåħĪ
    -0.26
    Jwt
    -0.25
    ç©¿éĢı
    -0.25
    æµĨ
    -0.25
    pos
    -0.25
    é¦ĸä½į
    -0.24
    رÙĪع
    -0.24
     komb
    -0.24
    æŁĴ
    -0.23
    纪
    -0.23
    POSITIVE LOGITS
     clicking
    0.46
     click
    0.41
    çĤ¹åĩ»
    0.40
     toggle
    0.39
    -click
    0.38
     clickable
    0.38
     downloadable
    0.37
    æĮīéĴ®
    0.37
     clicked
    0.36
     togg
    0.36
    Activations Density 0.002%

    No Known Activations