© 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. 23154
    Prev
    Next
    INDEX
    Explanations

    handicap access

    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
    æ¡£
    -0.10
    зав
    -0.10
    Atl
    -0.10
    uido
    -0.10
    ļĮ
    -0.10
    fulness
    -0.10
    .Unlock
    -0.10
    uary
    -0.09
    ucky
    -0.09
    ctions
    -0.09
    POSITIVE LOGITS
    åįģ足
    0.10
    éĩįéĩį
    0.10
    æľīä¿¡å¿ĥ
    0.10
    ย
    0.10
    rames
    0.09
    äºĭä¸ļåıijå±ķ
    0.09
    ±
    0.09
    rus
    0.08
    äºĭä¸ļ
    0.08
    ä½ĵéĩį
    0.08
    Activations Density 0.002%

    No Known Activations