© 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. 19407
    Prev
    Next
    INDEX
    Explanations

    upper reaches, bound, tier, East, portion, airway

    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
    ually
    -0.10
    ä¸ĬåįĪ
    -0.09
    osphere
    -0.09
    aded
    -0.09
    ä¸įå¼Ģ
    -0.09
    sar
    -0.08
    ging
    -0.08
    å²Ľä¸Ĭ
    -0.08
    sam
    -0.08
    sym
    -0.08
    POSITIVE LOGITS
    most
    0.21
    iores
    0.12
    MOST
    0.11
    draft
    0.11
    -than
    0.10
    halb
    0.10
    dater
    0.09
    idge
    0.09
    ahas
    0.09
    ç§įç§į
    0.09
    Activations Density 0.025%

    No Known Activations