© 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. 56642
    Prev
    Next
    INDEX
    Explanations

    science fiction

    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
    atively
    -0.10
    éĴ§
    -0.09
    UNS
    -0.09
    æ³¼
    -0.09
    .BOLD
    -0.09
    ÐIJÐĿ
    -0.08
    æĻ®
    -0.08
    éĥ¢
    -0.08
    _REDIRECT
    -0.08
    rea
    -0.08
    POSITIVE LOGITS
    ä¹İ
    0.10
     minded
    0.09
    ÑİÑĢ
    0.08
     ÑģÑĤеп
    0.08
    éģIJ
    0.08
    oose
    0.08
    ivist
    0.08
    workers
    0.08
    ierz
    0.08
    åħ¶æ¬¡
    0.08
    Activations Density 0.011%

    No Known Activations