© 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. 35199
    Prev
    Next
    INDEX
    Explanations

    wife or consort of

    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
    麻
    -0.09
    ugins
    -0.09
    妹åŃIJ
    -0.09
    è¿Ļ个éĹ®é¢ĺ
    -0.09
    éł
    -0.09
    opian
    -0.09
    åĶĩ
    -0.08
    èĪ¾
    -0.08
    TexCoord
    -0.08
    对åħ¬åı¸
    -0.08
    POSITIVE LOGITS
    亿ä¸ĩ
    0.10
    akk
    0.09
    主æµģ
    0.09
    èµ·çłģ
    0.09
    çıł
    0.08
    ä¿©
    0.08
    atre
    0.08
    骢
    0.08
    æĪĸå¤ļ
    0.08
    å¾Ģå¤ĸ
    0.08
    Activations Density 0.022%

    No Known Activations