© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9793
    Prev
    Next
    INDEX
    Explanations

    contact and accessibility

    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
    tam
    -0.09
    å¾Īåĸľæ¬¢
    -0.08
    ply
    -0.08
    æĪIJè´¥
    -0.08
    çĤ¹ç¼Ģ
    -0.08
    plemented
    -0.08
    onga
    -0.08
    åĩºæĿ¥çļĦ
    -0.08
    å®ĮæĪIJåIJİ
    -0.08
    ãģ¤ãģª
    -0.08
    POSITIVE LOGITS
    åŃº
    0.11
    миÑĢ
    0.10
     Jes
    0.10
    çľ¼éĩĮ
    0.10
    ä½ĵè´´
    0.10
    aversable
    0.09
    opus
    0.09
    ç±ģ
    0.09
    çĥ¦
    0.09
    .Undef
    0.09
    Activations Density 0.004%

    No Known Activations