© 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. 17376
    Prev
    Next
    INDEX
    Explanations

    use of

    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
    å¨ĩ
    -0.08
    ats
    -0.08
    æ·±åĪ»çļĦ
    -0.08
    çĴŀ
    -0.08
    -angular
    -0.08
    çĤ¸
    -0.08
    uper
    -0.08
    大çļĦ
    -0.08
    çıº
    -0.08
    åĪ¶
    -0.08
    POSITIVE LOGITS
    å¿Ļ
    0.09
    åŁĭ
    0.09
    éĺ³åı°
    0.09
    cks
    0.09
     fle
    0.09
    åĮħ袱
    0.08
    æĺ¾ç¤ºå±ı
    0.08
    åĽµ
    0.08
    acker
    0.08
    hythm
    0.08
    Activations Density 0.009%

    No Known Activations