© 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. 18580
    Prev
    Next
    INDEX
    Explanations

    python code

    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
    è¡ĮæĿİ
    -0.10
    овоÑĢ
    -0.09
     Bounty
    -0.09
    åĬŁå¾·
    -0.08
    Ñıн
    -0.08
    weis
    -0.08
    éŃ
    -0.08
    Õ²
    -0.08
    иÑĢов
    -0.08
    ä¸Ģè¶Ł
    -0.08
    POSITIVE LOGITS
    ively
    0.12
    åįģ足
    0.10
    ably
    0.10
    ðŁı»
    0.10
    ANCE
    0.10
    æ¡Ģ
    0.09
    á»ĩt
    0.09
    ly
    0.09
    OTE
    0.09
    ÑģÑĤвие
    0.09
    Activations Density 0.002%

    No Known Activations