© 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. 5256
    Prev
    Next
    INDEX
    Explanations

    naive

    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
     Rug
    -0.08
    æ¯Ĵ
    -0.08
    ings
    -0.08
    åŁºçŁ³
    -0.08
    ç²¾
    -0.08
    lights
    -0.08
    åıijå±ķè¶ĭåĬ¿
    -0.08
    -addons
    -0.08
    ummer
    -0.07
    icks
    -0.07
    POSITIVE LOGITS
    0.12
    å¨ħ
    0.10
    å«©
    0.09
    å¼ĢåѦ
    0.09
    æĢ§åĴĮ
    0.09
    æĥ³æ³ķ
    0.09
    cul
    0.09
    izr
    0.09
    -looking
    0.09
    å¸ĮæľĽèĥ½
    0.09
    Activations Density 0.006%

    No Known Activations