© 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. 52577
    Prev
    Next
    INDEX
    Explanations

    The process

    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
    aps
    -0.09
    åĸ·
    -0.09
    佬
    -0.09
    åĪ¶æĪIJ
    -0.09
    amo
    -0.08
    è·³
    -0.08
    åĻ´
    -0.08
    atto
    -0.08
     hop
    -0.08
     ба
    -0.08
    POSITIVE LOGITS
     process
    0.10
     пÑĢоÑĨеÑģÑģ
    0.10
    è¿Ľç¨ĭ
    0.10
     Process
    0.10
    process
    0.09
     candidacy
    0.09
    è¿ĩç¨ĭ
    0.09
    aina
    0.08
    oving
    0.08
     Sacred
    0.08
    Activations Density 0.031%

    No Known Activations