© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29686
    Prev
    Next
    INDEX
    Explanations

    Buffy the Vampire Slayer, Angel, Firefly

    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
     Pars
    -0.09
    伶
    -0.08
    otron
    -0.08
    åķ¤éħĴ
    -0.08
    åĮħ裹
    -0.08
    è¿ĺåİŁ
    -0.08
    Ùģار
    -0.08
    å°±ç®Ĺ
    -0.08
    使èĢħ
    -0.08
    å·¡åĽŀ
    -0.08
    POSITIVE LOGITS
    æ®Ĩ
    0.09
    /owl
    0.09
    .pretty
    0.08
    åľ¨ç½ijä¸Ĭ
    0.08
    涵
    0.08
    extras
    0.08
    èĶĹ
    0.08
    èĬĹ
    0.08
    è¥Ħ
    0.08
    anst
    0.08
    Activations Density 0.006%

    No Known Activations