© 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. 27083
    Prev
    Next
    INDEX
    Explanations

    point of view, narrating, techniques

    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
    èĥĥåı£
    -0.09
    rá
    -0.09
    å¾Ĵ
    -0.08
    éº
    -0.08
    æī°
    -0.08
    çIJĨçĶ±
    -0.08
    ç½Ħ
    -0.08
    çĨĬçĮ«
    -0.08
     slime
    -0.08
    梨
    -0.08
    POSITIVE LOGITS
    人çī©
    0.15
    çļĦ人çī©
    0.12
    第ä¸īèĢħ
    0.10
    第ä¸ī人
    0.10
     characters
    0.09
    æݺ
    0.09
    éĤ£æ¬¡
    0.09
    ãĥIJãĥ¬
    0.09
    ç«ĭåľº
    0.09
    æııåĨĻ
    0.09
    Activations Density 0.089%

    No Known Activations