© 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. 1194
    Prev
    Next
    INDEX
    Explanations

    body

    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
    èĦļä¸ĭ
    -0.10
    éĵĦ
    -0.09
    身æĹģ
    -0.09
    atk
    -0.09
    头顶
    -0.09
    çĵ¶åŃIJ
    -0.08
    andan
    -0.08
    æ¼Ĥæµģ
    -0.08
    pery
    -0.08
    onds
    -0.08
    POSITIVE LOGITS
    éĻĽ
    0.10
    ream
    0.09
    ENSE
    0.08
    ç»ıåķĨ
    0.08
    feito
    0.08
    æ©
    0.08
    åĴĮ社ä¼ļ
    0.08
    éĻĽä¸ĭ
    0.08
    çļĦåĬŁèĥ½
    0.08
    anson
    0.08
    Activations Density 0.016%

    No Known Activations