© 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. 43143
    Prev
    Next
    INDEX
    Explanations

    sac

    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
    PO
    -0.28
    缸
    -0.28
    pte
    -0.27
    å»ĵ
    -0.27
    oses
    -0.26
    æŀ¢
    -0.26
    à¸ľ
    -0.26
    OO
    -0.25
     Mech
    -0.25
    aptor
    -0.25
    POSITIVE LOGITS
    ertools
    0.31
    älle
    0.27
    æĭīå¼Ģ
    0.27
    央è¡Į
    0.26
    沿
    0.25
    éĺ²çģ«
    0.25
    åĿĩæľī
    0.25
    约åįł
    0.25
    å¾·æĭī
    0.24
    ecn
    0.24
    Activations Density 0.001%

    No Known Activations