© 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. 17239
    Prev
    Next
    INDEX
    Explanations

    caused by

    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
    ower
    -0.09
    oyo
    -0.08
    zer
    -0.08
    èįĴ
    -0.08
    -exclusive
    -0.08
    çķĢ
    -0.08
    LETE
    -0.08
     dõ
    -0.08
    ä¸ī天
    -0.08
    姤
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹ĪåİŁåĽł
    0.12
    è¿«
    0.10
    æĦŁ
    0.09
    è¡Įä¸ļåıijå±ķ
    0.09
    åı¯èĥ½æĺ¯
    0.09
    æĪĸ许æĺ¯
    0.09
    çĸij
    0.09
    меÑĢ
    0.09
    ivos
    0.08
    áŀ¡
    0.08
    Activations Density 0.099%

    No Known Activations