© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7443
    Prev
    Next
    INDEX
    Explanations

    absoluteness or entirety

    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
    uitive
    -0.09
    ers
    -0.08
    ur
    -0.08
     ÑģÑĤÑĢа
    -0.08
    æĪĺåĽ½
    -0.08
    patch
    -0.08
    aroo
    -0.08
    ами
    -0.08
    é¢ĩ为
    -0.08
    arious
    -0.08
    POSITIVE LOGITS
    eso
    0.10
    fare
    0.10
    åıijå±ķåīįæĻ¯
    0.10
    ä¸įçIJĨ
    0.10
    çIJĨä¼ļ
    0.09
    ivi
    0.09
    éĥ½èĥ½
    0.09
    è¡ĮæĶ¿éĥ¨éŨ
    0.09
    .unbind
    0.09
    rint
    0.09
    Activations Density 0.002%

    No Known Activations