© 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. 43784
    Prev
    Next
    INDEX
    Explanations

    belong

    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
    erable
    -0.29
     streamlined
    -0.28
    repid
    -0.24
    çľĭäºĨä¸Ģ
    -0.24
     realized
    -0.24
    amed
    -0.23
    AUTHORIZED
    -0.23
    /Internal
    -0.23
     Fam
    -0.23
    æł¹æį®ä¸įåIJĮ
    -0.23
    POSITIVE LOGITS
     to
    0.31
    åĶ¯
    0.30
     technically
    0.29
    loyd
    0.29
     democr
    0.28
     explicitly
    0.28
     territor
    0.27
    æ®·
    0.27
     fur
    0.27
     nomin
    0.27
    Activations Density 0.004%

    No Known Activations