© 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. 41562
    Prev
    Next
    INDEX
    Explanations

    motivation, beliefs, and desires

    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
     Trades
    -0.29
    indsight
    -0.27
    åĩºçİ°
    -0.26
     Dominion
    -0.26
    itecture
    -0.26
     domin
    -0.26
    hm
    -0.25
    ä½ıæīĢ
    -0.24
    /wp
    -0.24
    éĻ·åħ¥äºĨ
    -0.24
    POSITIVE LOGITS
     breeds
    0.34
    åħ»
    0.33
     solid
    0.31
     shapes
    0.30
     cultiv
    0.30
    让æĤ¨
    0.29
     fost
    0.28
     allows
    0.27
     equ
    0.27
    eyer
    0.27
    Activations Density 0.002%

    No Known Activations