© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54801
    Prev
    Next
    INDEX
    Explanations

    control of vehicle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çŀ½
    -0.10
    åIJĮåŁİ
    -0.09
    çĥ
    -0.09
    çijľ
    -0.08
    ibility
    -0.08
    hud
    -0.08
    å¸ĮæľĽèĥ½
    -0.08
    AINS
    -0.08
    è®°
    -0.08
    åľ¨åħ¨åĽ½
    -0.08
    POSITIVE LOGITS
    itto
    0.10
    ç«ĭ足
    0.09
    åıªè§ģ
    0.08
    åķĨçĶ¨
    0.08
    .cod
    0.08
    è¾Ł
    0.08
    imus
    0.08
    åĥ»
    0.08
    _MALLOC
    0.08
    acie
    0.08
    Activations Density 0.035%

    No Known Activations