© 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. 62050
    Prev
    Next
    INDEX
    Explanations

    notify if error

    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
     Vent
    -0.09
    Scalars
    -0.09
    VENT
    -0.08
    ãĤŃãĥ¥
    -0.08
    溶解
    -0.08
    cow
    -0.08
    æĴŃ
    -0.08
    tid
    -0.08
    ست
    -0.08
    欢è¿İæĤ¨
    -0.08
    POSITIVE LOGITS
    æ´ª
    0.09
    以便
    0.09
     ká»ĭp
    0.09
    å°½æĹ©
    0.09
    ä»»ä½ķæŶåĢĻ
    0.09
    çĻĸ
    0.09
    ç§ĺ书éķ¿
    0.09
    _bits
    0.09
    æ»ŀåIJİ
    0.09
    羣æĥħ
    0.08
    Activations Density 0.027%

    No Known Activations