© 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. 10367
    Prev
    Next
    INDEX
    Explanations

    price

    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
    éŃĦ
    -0.10
    æŃ£åĵģ
    -0.10
    åĴĮåľ°åĮº
    -0.09
    _RCC
    -0.09
    è¿
    -0.09
    è¹ĩ
    -0.09
    translated
    -0.08
    åĴĮæľįåĬ¡
    -0.08
    isu
    -0.08
    lah
    -0.08
    POSITIVE LOGITS
    ably
    0.15
    0.12
    baugh
    0.11
    ABLE
    0.10
    less
    0.09
    able
    0.09
    cmp
    0.09
    ØŃ
    0.09
    gerald
    0.09
    onom
    0.09
    Activations Density 0.012%

    No Known Activations