© 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. 48124
    Prev
    Next
    INDEX
    Explanations

    you know how

    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
    èĴĻ
    -0.09
    æĺİçĻ½
    -0.09
    hev
    -0.09
     fade
    -0.08
    æݧ
    -0.08
    çĩĥ
    -0.08
    antan
    -0.08
    æľ¬è´¨ä¸Ĭ
    -0.08
    cip
    -0.08
    æIJ¬åĪ°
    -0.08
    POSITIVE LOGITS
    itu
    0.10
    åī¯
    0.10
    æī«ä¸Ģæī«
    0.09
    åŃ³
    0.09
    _tpl
    0.09
    VERBOSE
    0.09
    éĵĨ
    0.09
    atif
    0.09
    æŀ¶
    0.08
    欹
    0.08
    Activations Density 0.024%

    No Known Activations