© 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. 17303
    Prev
    Next
    INDEX
    Explanations

    not limited to

    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
    æĹ¢æĺ¯
    -0.09
    ----</
    -0.09
    èĤ¢
    -0.08
    éŃĶ鬼
    -0.08
    iev
    -0.08
    CTYPE
    -0.08
    _tc
    -0.08
     tav
    -0.08
    oming
    -0.08
    /projects
    -0.08
    POSITIVE LOGITS
    äºİæѤ
    0.11
    opsis
    0.10
    çķħ
    0.09
    opoulos
    0.09
    ä»ħä»ħ
    0.09
    äºİ
    0.08
    onyms
    0.08
    éĵ¡
    0.08
    ä¸ĢåIJį
    0.08
    å¿«æĬ¥
    0.08
    Activations Density 0.011%

    No Known Activations