© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21094
    Prev
    Next
    INDEX
    Explanations

    FILING ORIMPLEMENTS

    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
    s
    -0.12
    esson
    -0.09
    æŁ¯
    -0.09
    eldo
    -0.09
    atorio
    -0.09
    ivable
    -0.08
    Äĩ
    -0.08
    ocado
    -0.08
    rim
    -0.08
    ivity
    -0.08
    POSITIVE LOGITS
    ä¸ĢåįĬ
    0.09
    è´»
    0.09
    ä¸Ģåıªæīĭ
    0.09
    èĭ¦æģ¼
    0.09
    -heavy
    0.08
    .isPresent
    0.08
    æķ²
    0.08
    avra
    0.08
    burgh
    0.08
    borough
    0.08
    Activations Density 0.046%

    No Known Activations