© 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. 31326
    Prev
    Next
    INDEX
    Explanations

    submit feedback or questions

    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
    iated
    -0.10
    åģļ大
    -0.09
     Hope
    -0.08
    éĿ©
    -0.08
    rv
    -0.08
    unden
    -0.08
    mtx
    -0.08
    isc
    -0.08
    iable
    -0.07
    Hope
    -0.07
    POSITIVE LOGITS
    è¸Ĭè·ĥ
    0.11
    è´¡çĮ®
    0.10
    åıįé¦Ī
    0.10
    æİ¥åĬĽ
    0.10
    åıªè¦ģæĺ¯
    0.10
    åĵªæĢķæĺ¯
    0.10
    æĤĦæĤĦ
    0.10
    åĨĻåĩº
    0.09
    åıįåĩ»
    0.09
    åĮ¿åIJį
    0.09
    Activations Density 0.055%

    No Known Activations