© 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. 2394
    Prev
    Next
    INDEX
    Explanations

    family owned or related

    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
    éĢīæĭ
    -0.09
    æĭīçĿĢ
    -0.09
    é³ħ
    -0.09
    Mor
    -0.09
    ylie
    -0.09
    æŃ¢
    -0.09
    ç»Ĭ
    -0.09
    ÑģÑĤÑĥп
    -0.08
    轸
    -0.08
    (zip
    -0.08
    POSITIVE LOGITS
     family
    0.17
    家æĹı
    0.16
    -family
    0.15
    family
    0.15
    _family
    0.14
    家åºŃ
    0.13
    家å±ŀ
    0.12
    家人
    0.12
     famil
    0.12
    家çĶ¨
    0.11
    Activations Density 0.093%

    No Known Activations