© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9619
    Prev
    Next
    INDEX
    Explanations

    music album or collection

    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´±
    -0.09
     countdown
    -0.09
    missive
    -0.09
    presso
    -0.09
    Å¡ÃŃ
    -0.09
    éĹ¾
    -0.09
    Ä°R
    -0.09
     Æ°u
    -0.09
    _locs
    -0.08
    污
    -0.08
    POSITIVE LOGITS
     African
    0.09
     Trio
    0.09
    Solo
    0.09
     бон
    0.08
    æĦŁäºº
    0.08
    太æŀģæĭ³
    0.08
    éļ¶
    0.08
    .lazy
    0.08
    æ»´
    0.08
    æIJŃæ¡£
    0.08
    Activations Density 0.075%

    No Known Activations