© 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. 17968
    Prev
    Next
    INDEX
    Explanations

    surname suffixes

    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
    æĸ°å½¢åĬ¿ä¸ĭ
    -0.11
    ÐĽÐŀ
    -0.10
    ibi
    -0.09
    pace
    -0.09
    PACE
    -0.09
    åĪĿ次
    -0.09
    çļĭ
    -0.09
    _setup
    -0.09
    æ½®
    -0.09
    OLID
    -0.09
    POSITIVE LOGITS
    dal
    0.10
    åİ®
    0.09
    ers
    0.09
    أش
    0.09
    éĢĭ
    0.09
     Buen
    0.09
    黾
    0.09
    uye
    0.09
    交éĶĻ
    0.08
    åķ°
    0.08
    Activations Density 0.080%

    No Known Activations