© 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. 41835
    Prev
    Next
    INDEX
    Explanations

    Ordinal number suffixes

    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
    è´¼
    -0.27
    agate
    -0.26
     adher
    -0.26
    æµģ产
    -0.25
    nt
    -0.25
     resale
    -0.25
     offers
    -0.24
    éķ¿éķ¿
    -0.24
     offer
    -0.24
     instrument
    -0.23
    POSITIVE LOGITS
    amide
    0.29
    /dir
    0.28
    etten
    0.27
    etri
    0.26
    ableObject
    0.26
    edly
    0.25
    æĿ¥ä¸įåıĬ
    0.25
     seg
    0.24
     Gu
    0.24
     trouve
    0.24
    Activations Density 0.003%

    No Known Activations