© 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. 61951
    Prev
    Next
    INDEX
    Explanations

    mother, parent, child relationships

    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
    åģ¥åº·æĪIJéķ¿
    -0.10
     aff
    -0.09
    èĿĮ
    -0.09
    ouden
    -0.08
    åħ¬çĶ¨
    -0.08
    大çĪ·
    -0.08
    åħ±æľī
    -0.08
    éĽĨåIJĪ
    -0.08
    磫
    -0.08
     girlfriend
    -0.08
    POSITIVE LOGITS
    对åŃ©åŃIJ
    0.17
    ç»ĻåŃ©åŃIJ
    0.14
    ä¸Ī夫
    0.12
    èĤ²åĦ¿
    0.12
    让åŃ©åŃIJ
    0.11
    å¨ĺ家
    0.10
    åŃ©åŃIJ
    0.10
    èģĮ称
    0.10
    产åIJİ
    0.10
    妯
    0.10
    Activations Density 0.088%

    No Known Activations