© 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. 111842
    Prev
    Next
    INDEX
    Explanations

    Code/Foreign languages

    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
    boys
    -0.28
    çĭ¼
    -0.27
    ãĥ¥ãĥ¼
    -0.26
    éķ¿åŁİ
    -0.25
    -setting
    -0.25
     boys
    -0.25
     Boys
    -0.25
    çī©
    -0.25
    ibil
    -0.25
    uit
    -0.25
    POSITIVE LOGITS
    åľ¨æİ¥åıĹ
    0.30
    éĤ¸
    0.28
     =&
    0.27
    箪
    0.27
    æ·ĺ
    0.24
     Operating
    0.24
    åľ¨è¿ĩæ¸¡æľŁ
    0.24
    ä½İåİĭ
    0.24
     garner
    0.24
    .TestCheck
    0.23
    Activations Density 0.157%

    No Known Activations