© 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. 63663
    Prev
    Next
    INDEX
    Explanations

    as/like/follow + description/example/instruction

    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
    èĸĦ
    -0.09
    纵è§Ĥ
    -0.09
    olvers
    -0.08
    >Type
    -0.08
    ä¸ī级
    -0.08
    ometrics
    -0.08
     elect
    -0.08
    æĽĻåħī
    -0.08
    è¿©
    -0.08
    adow
    -0.08
    POSITIVE LOGITS
    æĸ¹å¼ıè¿Ľè¡Į
    0.11
    åī§æĥħ
    0.09
    æŃ¥éª¤
    0.09
    æ¶īå«Į
    0.09
     usual
    0.09
    éĢļãĤĬ
    0.09
    å¦Ĥä¸ĭ
    0.09
     way
    0.09
    èĭ±æīį
    0.09
    éľģ
    0.09
    Activations Density 0.214%

    No Known Activations