© 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. 7202
    Prev
    Next
    INDEX
    Explanations

    reject

    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
    ycop
    -0.10
    ç¤ģ
    -0.09
    åºķæ°Ķ
    -0.09
    razione
    -0.09
    äch
    -0.09
    uko
    -0.09
    å¹Ħ
    -0.09
    imps
    -0.08
    ãĤ£
    -0.08
    ç²¥
    -0.08
    POSITIVE LOGITS
    ively
    0.15
    ive
    0.14
    ably
    0.12
    åħļçļĦé¢Ĩ导
    0.10
    able
    0.10
    edException
    0.10
    æ»ĵ
    0.10
    amma
    0.10
     tá»ij
    0.10
    æİīäºĨ
    0.09
    Activations Density 0.017%

    No Known Activations