© 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. 1032
    Prev
    Next
    INDEX
    Explanations

    Slayer, property, opinions

    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
    erer
    -0.08
    ç´§ç´§åĽ´ç»ķ
    -0.08
     itself
    -0.08
    仡
    -0.08
    quer
    -0.08
    æŃ£åľ¨
    -0.08
    奶
    -0.08
    é²ĩ
    -0.08
    åĨ¶
    -0.08
    æĢı
    -0.08
    POSITIVE LOGITS
    lords
    0.09
    ç²Ĺ
    0.09
    ếp
    0.09
    каж
    0.08
    ç»Ħç»ĩé¢Ĩ导
    0.08
    å²ł
    0.08
    CCA
    0.08
    .hashCode
    0.08
    ModelState
    0.08
    Teacher
    0.08
    Activations Density 0.020%

    No Known Activations