© 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. 2810
    Prev
    Next
    INDEX
    Explanations

    many followed by quantity/variety descriptors

    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
    çĦ¶æĺ¯
    -0.12
    ate
    -0.10
    æŁIJç§į
    -0.09
    æŁIJäºĽ
    -0.09
    imate
    -0.09
     immense
    -0.09
    ious
    -0.09
     kê
    -0.09
    cott
    -0.09
    æł¼å°Ķ
    -0.09
    POSITIVE LOGITS
    ToMany
    0.15
    /all
    0.12
    -sided
    0.11
    æĻĤåĢĻ
    0.11
    THING
    0.10
    ÑĩиÑģлен
    0.10
     à¹Ĩ
    0.10
    çĵ¢
    0.10
    ToOne
    0.10
    yyy
    0.10
    Activations Density 0.076%

    No Known Activations