© 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. 55646
    Prev
    Next
    INDEX
    Explanations

    hyphenated last names

    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
    ç¼±
    -0.10
    äºĵ
    -0.09
    пÑĢоÑģ
    -0.08
    失信
    -0.08
    项éĵ¾
    -0.08
    /inc
    -0.08
     afs
    -0.08
    atal
    -0.08
    åıijå±ķåīįæĻ¯
    -0.08
    å¾ľ
    -0.08
    POSITIVE LOGITS
    第ä¸Ģ天
    0.10
    !--
    0.09
    erness
    0.09
    scheme
    0.09
    Net
    0.09
     Fowler
    0.09
    adier
    0.08
    å¾Ĵ
    0.08
    .Net
    0.08
    严éĩįçļĦ
    0.08
    Activations Density 0.165%

    No Known Activations