© 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. 48327
    Prev
    Next
    INDEX
    Explanations

    JICO, Colby College, Washington, Zend

    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
    éĶ£
    -0.10
    riot
    -0.10
    天èĬ±
    -0.08
    è¿ŀäºij
    -0.08
    缴éĢļ车
    -0.08
    ãĤŃãĥ³
    -0.08
    é¢Ħè§ģ
    -0.08
    çĹħ
    -0.08
    mux
    -0.08
    çģ¯ç¬¼
    -0.08
    POSITIVE LOGITS
    hape
    0.10
    æݺ
    0.09
    人为
    0.09
    碰
    0.09
    åĽ¢
    0.09
    çѱ
    0.08
    èĢĹ
    0.08
    6
    0.08
    æīĢè°ĵçļĦ
    0.08
     sen
    0.08
    Activations Density 0.002%

    No Known Activations