© 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. 57725
    Prev
    Next
    INDEX
    Explanations

    list item marker

    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
    çļĦç¼ĺ
    -0.10
    stead
    -0.09
    ********
    -0.08
    çīĸ
    -0.08
    å»Ľ
    -0.08
    elian
    -0.07
    _rq
    -0.07
     sticks
    -0.07
    moz
    -0.07
    åŁł
    -0.07
    POSITIVE LOGITS
    args
    0.10
     маÑĤеÑĢиал
    0.10
    èįIJ
    0.10
    éķĬ
    0.10
    éĢĨè¡Į
    0.09
    (rawValue
    0.09
    æŃĩ
    0.09
    ï¸ı
    0.09
    æ¾İæ¹ĥ
    0.09
    ãģijãģ¦
    0.09
    Activations Density 0.100%

    No Known Activations