© 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. 18781
    Prev
    Next
    INDEX
    Explanations

    performing tricks, riding a, fan for, star wants

    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
    éĤ£éĩĮ
    -0.09
    åĥ®
    -0.09
    åħ¬çĶ¨
    -0.09
    èĥ´
    -0.08
    /browser
    -0.08
    nten
    -0.08
     ÑĩиÑģле
    -0.08
    赶快
    -0.08
    èĽĨ
    -0.08
    ione
    -0.08
    POSITIVE LOGITS
    æ¸ħåįİ
    0.09
    æŶå°ļ
    0.09
    WARE
    0.09
    æĬķå½±
    0.09
    éĦ£
    0.09
    移åĬ¨
    0.08
    è¿Ļ款
    0.08
    LIKE
    0.08
    unlikely
    0.08
    _AST
    0.08
    Activations Density 0.145%

    No Known Activations