© 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. 57680
    Prev
    Next
    INDEX
    Explanations

    enthusiast/enthusiasts

    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
    ton
    -0.10
    åħ·
    -0.09
    ØŃت
    -0.09
    à¹Ģà¸Ńà¸ĩ
    -0.09
    cheon
    -0.09
    侧ç»ĵæŀĦæĢ§
    -0.08
    otte
    -0.08
    erture
    -0.08
    æ±²
    -0.08
    inary
    -0.08
    POSITIVE LOGITS
    ä¹İ
    0.12
    amble
    0.10
    ful
    0.10
    åĭĥåĭĥ
    0.10
    ä¸įå·²
    0.09
    iasm
    0.09
    osc
    0.09
    æ¤Ĵ
    0.09
    elves
    0.09
    AndWait
    0.09
    Activations Density 0.006%

    No Known Activations