© 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. 3983
    Prev
    Next
    INDEX
    Explanations

    from to through

    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
    hat
    -0.09
    6
    -0.09
    å¿Ĵ
    -0.08
    7
    -0.08
    è¾ĭ
    -0.08
     Chamber
    -0.08
    åŁĴ
    -0.08
    amas
    -0.08
    .messaging
    -0.08
    0
    -0.08
    POSITIVE LOGITS
    åĨįåĪ°
    0.25
    ä¸Ģ缴åĪ°
    0.18
    åĪ°
    0.18
    åĪ°æľĢåIJİ
    0.16
    èĩ³
    0.14
    åĪ°çİ°åľ¨
    0.14
    缴èĩ³
    0.13
     Ø¥ÙĦÙī
    0.13
     ×ķ×¢×ĵ
    0.12
    ä¹ĥèĩ³
    0.12
    Activations Density 0.077%

    No Known Activations