© 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. 58953
    Prev
    Next
    INDEX
    Explanations

    contracts and options

    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
     nd
    -0.08
    éĢŀ
    -0.08
    عدÙĦ
    -0.08
     Alg
    -0.08
    веÑĢ
    -0.08
    楼
    -0.08
    æģĥ
    -0.08
    æŃ£å½ĵ
    -0.08
    Alg
    -0.07
     ru
    -0.07
    POSITIVE LOGITS
    gmt
    0.10
    achen
    0.09
    ÐĦ
    0.09
    akan
    0.09
     Kov
    0.09
    icts
    0.08
    æľĿ
    0.08
    Datum
    0.08
    éĩįéĩį
    0.08
    isz
    0.08
    Activations Density 0.022%

    No Known Activations