© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10569
    Prev
    Next
    INDEX
    Explanations

    " or ‘

    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
    èĩªçĦ¶èĢĮ
    -0.10
    管çIJĨåĴĮ
    -0.09
    åİŁåīĩ
    -0.09
    ç»ıéªĮåĴĮ
    -0.09
    è¿ĺæĺ¯ä¼ļ
    -0.09
    è´¶
    -0.09
    åĬĽãĤĴ
    -0.09
    äºĨåĩł
    -0.08
    elters
    -0.08
     Princip
    -0.08
    POSITIVE LOGITS
    /or
    0.17
    /OR
    0.13
    phans
    0.10
    acular
    0.10
     consequ
    0.10
     tháºŃm
    0.10
    ifice
    0.10
    çĶļèĩ³æĺ¯
    0.09
     possibly
    0.09
    ãģĿãģĹãģ¦
    0.09
    Activations Density 0.145%

    No Known Activations