© 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. 43488
    Prev
    Next
    INDEX
    Explanations

    programming and coding

    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
     development
    -0.30
    ued
    -0.28
    -cache
    -0.27
    _managed
    -0.26
     black
    -0.26
    _CACHE
    -0.25
    ·¨
    -0.25
    -c
    -0.25
    é»ij
    -0.25
    ç¼ĵ
    -0.25
    POSITIVE LOGITS
    ãĥ§ãĥ³
    0.25
    burn
    0.25
    æĸ¯å¡Ķ
    0.25
    纯æ´ģ
    0.24
    ´t
    0.24
    plevel
    0.23
     B
    0.23
    á»ģm
    0.23
    款
    0.23
    rip
    0.23
    Activations Density 0.050%

    No Known Activations