© 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. 4429
    Prev
    Next
    INDEX
    Explanations

    Signs of recognition and judgement

    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
    éģ¨
    -0.09
    èĨı
    -0.09
    æĪijåĸľæ¬¢
    -0.08
    åŁİéķĩ
    -0.08
    éĺIJæĺİ
    -0.08
    èĽĻ
    -0.08
    åĩ½
    -0.08
    PathParam
    -0.08
    è´¨
    -0.08
    çijķ
    -0.08
    POSITIVE LOGITS
    åĪ¤æĸŃ
    0.15
    å¯Łè§ī
    0.14
    è¯ĨåĪ«
    0.13
    æķıéĶIJ
    0.12
    å¯Ł
    0.11
     Signs
    0.11
     signs
    0.11
    åı¯çĸij
    0.10
    迹象
    0.10
    é¢ĦèѦ
    0.10
    Activations Density 0.129%

    No Known Activations