© 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. 62410
    Prev
    Next
    INDEX
    Explanations

    Osama, quote, Q, al, Sword

    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
    IRC
    -0.10
    è¾ķ
    -0.09
    apus
    -0.09
    uries
    -0.09
    ä¸įä¿¡
    -0.09
    å°ıå·§
    -0.09
    微信åħ¬ä¼Ĺ
    -0.09
    aggio
    -0.09
    çµ®
    -0.09
    wives
    -0.09
    POSITIVE LOGITS
    ç°¿
    0.11
    1
    0.10
    -lib
    0.09
    2
    0.09
    6
    0.08
    9
    0.08
    8
    0.08
    3
    0.08
    HW
    0.08
    4
    0.08
    Activations Density 0.006%

    No Known Activations