© 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. 39808
    Prev
    Next
    INDEX
    Explanations

    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
    èĤļ
    -0.11
     Kush
    -0.10
    æıIJçİ°
    -0.09
    lessness
    -0.09
    ä¸įç®¡ä½ł
    -0.09
    ä¸Ģç¬Ķ
    -0.09
    ama
    -0.09
    Õµ
    -0.08
    holds
    -0.08
    èµ·çĤ¹
    -0.08
    POSITIVE LOGITS
    æĽ´å¤ļ
    0.09
    aal
    0.09
    å°ıå¾®
    0.09
    è¿ĩå¤ļ
    0.09
    æ½ľ
    0.09
    vvm
    0.09
    andon
    0.08
    åħ¬çº¦
    0.08
     Plenty
    0.08
    _raise
    0.08
    Activations Density 0.002%

    No Known Activations