© 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. 38739
    Prev
    Next
    INDEX
    Explanations

    variable context

    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
    注éĩį
    -0.09
    åĩºåĬ¨
    -0.09
    ä¸Ģéģĵ
    -0.08
    è´£
    -0.08
    幺
    -0.08
    å½¢æĪIJäºĨ
    -0.08
    ,void
    -0.08
    APS
    -0.08
    èĩªå®¶
    -0.08
    æ´¾åĩº
    -0.08
    POSITIVE LOGITS
    åıĺéĩı
    0.18
     variables
    0.17
     пеÑĢемен
    0.15
     ë³ĢìĪĺ
    0.15
     variable
    0.14
     Variables
    0.14
    Variables
    0.13
    variables
    0.13
    .variables
    0.12
    _VARIABLE
    0.12
    Activations Density 1.131%

    No Known Activations