© 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. 58980
    Prev
    Next
    INDEX
    Explanations

    government spending and appropriations

    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
    çĶ¸
    -0.10
    çķĭ
    -0.09
    å¼Ĥåľ°
    -0.09
    elog
    -0.08
     Courier
    -0.08
    æĦŁ
    -0.08
    人人éĥ½
    -0.08
    亲
    -0.08
    _atts
    -0.08
    /reference
    -0.08
    POSITIVE LOGITS
    mate
    0.12
    æ³ķæ¡Ī
    0.11
    صÙĦا
    0.11
    è´µ
    0.11
     mate
    0.10
     mates
    0.10
    è®®æ¡Ī
    0.09
    åĮ®
    0.09
    unic
    0.09
    迷人
    0.09
    Activations Density 0.089%

    No Known Activations