© 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. 43289
    Prev
    Next
    INDEX
    Explanations

    Politics and countries

    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
     viz
    -0.27
    stin
    -0.26
    quirer
    -0.26
    writers
    -0.26
    harma
    -0.25
     california
    -0.25
    orca
    -0.24
    ensex
    -0.24
    celand
    -0.24
    éĽª
    -0.24
    POSITIVE LOGITS
    èĦij
    0.26
    æģĻ
    0.26
    çĶ·åŃ©
    0.26
     gut
    0.25
    ä¸įåĨįæĺ¯
    0.25
    åıĺéĩı
    0.25
     gone
    0.25
    è¿Ļ份
    0.24
    æ³Ľ
    0.24
    SURE
    0.24
    Activations Density 0.001%

    No Known Activations