© 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. 19474
    Prev
    Next
    INDEX
    Explanations

    twin pairs

    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
    è¡·
    -0.09
    åijĺ
    -0.09
    WARD
    -0.09
    æķ´é¡¿
    -0.09
    och
    -0.08
    vik
    -0.08
    å¸ĪèĮĥ大åѦ
    -0.08
    åħħæ²Ľ
    -0.08
    æ·±å±Ĥ次
    -0.08
    instein
    -0.08
    POSITIVE LOGITS
    hood
    0.12
    们çļĦ
    0.11
    æĪĸå¤ļ
    0.11
    åĢij
    0.11
    å§Ĭ妹
    0.11
    ships
    0.10
    ì¦Ī
    0.10
    ëij¥
    0.10
    ided
    0.09
    å§IJ妹
    0.09
    Activations Density 0.007%

    No Known Activations