© 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. 23282
    Prev
    Next
    INDEX
    Explanations

    decision or outcome

    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
    åģ·
    -0.09
    lems
    -0.09
    ساÙħ
    -0.08
    ниÑĨ
    -0.08
    Ars
    -0.08
    lig
    -0.08
    LEM
    -0.08
    _draft
    -0.08
    lemn
    -0.07
    ligt
    -0.07
    POSITIVE LOGITS
    ä»»ä½ķ人
    0.11
     indeed
    0.10
    æ»ļæ»ļ
    0.09
    ä»»ä½ķä¸Ģ个
    0.09
    龸éģĵ
    0.09
    社ä¼ļå®ŀè·µ
    0.09
    被åĬ¨
    0.09
    確ãģĭãģ«
    0.09
    burgh
    0.09
    ghost
    0.09
    Activations Density 0.052%

    No Known Activations