© 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. 55138
    Prev
    Next
    INDEX
    Explanations

    wizard setup or advisor guidance

    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
    æ²¥
    -0.09
    ç©·
    -0.08
    è¾IJ
    -0.08
    éĩįè¦ģæĮĩ示
    -0.08
    äºĭåħĪ
    -0.08
    ainen
    -0.08
    ivant
    -0.08
    çļĦ认åı¯
    -0.08
    elin
    -0.08
    çļĦåĬ¨ä½ľ
    -0.08
    POSITIVE LOGITS
    peg
    0.09
    åĴĮæĶ¯æĮģ
    0.09
    æľŁéĹ´
    0.09
    åIJĬ
    0.08
    æľŁåĨħ
    0.08
    pires
    0.08
    ÑģоÑģ
    0.08
    é½IJé²ģ
    0.08
    æĦŁ
    0.08
    åī²
    0.08
    Activations Density 0.016%

    No Known Activations