© 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. 27381
    Prev
    Next
    INDEX
    Explanations

    git commit

    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
    æģĤ
    -0.10
    поÑĩ
    -0.10
    åĪ¶èį¯
    -0.08
    throp
    -0.08
    æ´Ļ
    -0.08
    çŃĿ
    -0.08
    zenie
    -0.08
    usi
    -0.08
    ç¿Ģ
    -0.08
    ienia
    -0.08
    POSITIVE LOGITS
    _a
    0.17
    èį¯ä¸ļ
    0.17
    ÐIJ
    0.16
    ãĤ¢
    0.15
    A
    0.15
    Ａ
    0.15
    _A
    0.14
    a
    0.14
    າ
    0.14
     A
    0.14
    Activations Density 0.625%

    No Known Activations