© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8170
    Prev
    Next
    INDEX
    Explanations

    trying out

    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
    è´º
    -0.10
    æĭ¯
    -0.09
    é¦Ļ
    -0.09
    hunt
    -0.09
    PELL
    -0.09
    æĪijä¸įçŁ¥éģĵ
    -0.09
    æIJŀ好
    -0.08
    OfType
    -0.08
    VD
    -0.08
    yles
    -0.08
    POSITIVE LOGITS
    imonials
    0.11
    çľĭçľĭ
    0.10
     goose
    0.09
    èģĬèģĬ
    0.09
    imonial
    0.09
    ä¸Ģä¸ĭ
    0.09
    sWith
    0.08
    éĹ®éĹ®
    0.08
    éĻįèIJ½
    0.08
    _COMMIT
    0.08
    Activations Density 0.005%

    No Known Activations