© 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. 4183
    Prev
    Next
    INDEX
    Explanations

    this followed by context

    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
    羣æŃ£çļĦ
    -0.10
    ediator
    -0.08
    羣æŃ£
    -0.08
    éħ·
    -0.08
     Middleton
    -0.08
    è¿Ļç§įæĥħåĨµ
    -0.08
    ĺ
    -0.08
    WithValue
    -0.08
    éģį
    -0.08
    ç©¿æ¢Ń
    -0.07
    POSITIVE LOGITS
    åŃķ
    0.09
    ErrorException
    0.09
    èİŀ
    0.08
    äu
    0.08
    ilton
    0.08
    åŀĵ
    0.08
    ÄŁini
    0.08
     اÙĦØ®ÙĦÙĬ
    0.08
     ка
    0.08
    eln
    0.08
    Activations Density 0.240%

    No Known Activations