© 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. 41791
    Prev
    Next
    INDEX
    Explanations

    car

    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
    arial
    -0.29
    èıĮ
    -0.29
    pine
    -0.28
    epy
    -0.27
    SSIP
    -0.24
    erals
    -0.24
    ãģ¤ãģĦ
    -0.24
     satisfying
    -0.23
    ä½łä¹Ł
    -0.23
    craft
    -0.23
    POSITIVE LOGITS
    ot
    0.35
    oyo
    0.29
    mez
    0.29
    oto
    0.28
    oten
    0.28
     ot
    0.26
    ote
    0.26
    otre
    0.26
    ocide
    0.25
    ots
    0.25
    Activations Density 0.005%

    No Known Activations