© 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. 34888
    Prev
    Next
    INDEX
    Explanations

    gas

    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
    ego
    -0.10
    æ½Ķ
    -0.10
    ç»ıæµİä½ĵ
    -0.10
    ê±°
    -0.09
    å§Ĺ
    -0.09
    edor
    -0.09
    اظ
    -0.09
    eting
    -0.09
    輯
    -0.09
    evil
    -0.09
    POSITIVE LOGITS
    dem
    0.10
    pit
    0.10
    _UNICODE
    0.09
    ëģĶ
    0.09
    oline
    0.09
     اÙĦطبÙĬعÙĬ
    0.09
    ified
    0.09
    иков
    0.09
    ifiable
    0.09
    ification
    0.09
    Activations Density 0.021%

    No Known Activations