© 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. 22512
    Prev
    Next
    INDEX
    Explanations

    question phrases

    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
    ä¸ĢèĪ¬æĿ¥è¯´
    -0.09
    emap
    -0.08
    gest
    -0.08
     вÑģ
    -0.08
    /MM
    -0.08
    éĩįçĤ¹é¡¹çĽ®
    -0.08
    uve
    -0.08
    ENDOR
    -0.08
    ä¾ĽéľĢ
    -0.07
    è¡Ķ
    -0.07
    POSITIVE LOGITS
    odore
    0.09
    æ»ĵ
    0.08
    issions
    0.08
    ä¸įäºĨ
    0.08
    åĺīå¹´åįİ
    0.08
    éĺħ读åħ¨æĸĩ
    0.08
    èµ°ä¸ĭåİ»
    0.08
    è¶ħæłĩ
    0.08
    èѦåĬ¡
    0.08
    è´¨åľ°
    0.08
    Activations Density 0.447%

    No Known Activations