© 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. 87296
    Prev
    Next
    INDEX
    Explanations

    code

    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
    çĦ¦
    -0.31
    åģļæ³ķ
    -0.28
    éĢIJ
    -0.28
    人为
    -0.27
    æij©
    -0.26
    çĤİ
    -0.25
     cuid
    -0.25
    åīįæıIJ
    -0.24
    åİ»
    -0.24
    führer
    -0.24
    POSITIVE LOGITS
    综åIJĪå®ŀåĬĽ
    0.29
     ages
    0.27
    ture
    0.27
    etical
    0.25
    -west
    0.24
    _Component
    0.24
    æľĢåĸľæ¬¢
    0.24
    коп
    0.24
    约åIJĪ
    0.23
     whites
    0.23
    Activations Density 0.002%

    No Known Activations