© 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. 3972
    Prev
    Next
    INDEX
    Explanations

    chess tournament valuations

    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
    па
    -0.10
    çĭŃ
    -0.10
    odes
    -0.09
    egt
    -0.09
    unken
    -0.09
    åı¯è§ģ
    -0.09
     Baxter
    -0.09
    éĺŁéķ¿
    -0.09
    ä»ĭ
    -0.09
    ä¸įå¿į
    -0.09
    POSITIVE LOGITS
     Kr
    0.10
    Kr
    0.09
    åį¡éĢļ
    0.09
    æ°´æºIJ
    0.09
    _LOOKUP
    0.08
    Tes
    0.08
    fur
    0.08
    æįĤ
    0.08
    /examples
    0.08
    ig
    0.08
    Activations Density 0.026%

    No Known Activations