© 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. 32-TRANSCODER-HP
    7. 42951
    Prev
    Next
    INDEX
    Explanations

    environment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åįı
    -0.28
    ouser
    -0.28
    ä»ĺè´¹
    -0.28
    ç»Ħç»ĩå®ŀæĸ½
    -0.26
     Duty
    -0.26
     far
    -0.26
     sınıf
    -0.26
    æī¿æİ¥
    -0.25
    far
    -0.24
    åįĪåIJİ
    -0.24
    POSITIVE LOGITS
    environment
    0.33
     environmental
    0.32
     environment
    0.31
    çݯå¢ĥä¿ĿæĬ¤
    0.30
    çݯå¢ĥ
    0.30
    çĴ°å¢ĥ
    0.30
    æ¸ħæ´ģ
    0.29
    stag
    0.28
    Environment
    0.28
    /environment
    0.28
    Activations Density 0.001%

    No Known Activations