© 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. 43336
    Prev
    Next
    INDEX
    Explanations

    Encryption and code

    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
    Par
    -0.26
    壳
    -0.26
    par
    -0.26
    ä»ĺ
    -0.25
     Par
    -0.25
     MD
    -0.25
    POR
    -0.25
    паÑĢ
    -0.25
     kart
    -0.24
     кÑĢай
    -0.24
    POSITIVE LOGITS
    绾
    0.27
    dds
    0.27
    iku
    0.26
    æļ´éľ²
    0.26
    /stdc
    0.26
    è§Ħ磩
    0.25
     advertise
    0.25
    unds
    0.25
    çĦ¡æĸĻ
    0.25
    éĺ´éĺ³
    0.25
    Activations Density 0.007%

    No Known Activations