© 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. 49306
    Prev
    Next
    INDEX
    Explanations

    Lafayette Avenue store python Trade Records

    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
    æ¯ķä¸ļ
    -0.11
    罩
    -0.10
    å·¥ä¸ļåĽŃ
    -0.10
    åį®
    -0.10
    клÑİÑĩа
    -0.10
    æµħ
    -0.10
    è´·
    -0.09
    аниÑİ
    -0.09
    éĵİ
    -0.09
    dana
    -0.09
    POSITIVE LOGITS
    æģĭ
    0.08
    oid
    0.08
    ise
    0.08
     Hedge
    0.08
    oids
    0.07
    Tags
    0.07
    伫
    0.07
    ç¡®
    0.07
    occo
    0.07
    éĻ¬
    0.07
    Activations Density 0.005%

    No Known Activations