© 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. 12-TRANSCODER-HP
    7. 23220
    Prev
    Next
    INDEX
    Explanations

    major

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perk
    -0.33
    éĻįèĩ³
    -0.27
    reek
    -0.25
    ç²¾
    -0.24
     perks
    -0.24
    åŃĹæł·
    -0.24
    ats
    -0.23
    æµij
    -0.23
    è¡Ĺéģĵ
    -0.23
    åºļ
    -0.23
    POSITIVE LOGITS
    æĭ³å¤´
    0.32
    çĵ¦
    0.29
    è·º
    0.26
    æĬ¥åijĬæľŁåĨħ
    0.25
    èĬ¬
    0.24
     Treat
    0.24
    èĸ¤
    0.24
     movable
    0.24
     Oliv
    0.24
    ç³ħ
    0.24
    Activations Density 0.003%

    No Known Activations