© 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. 34564
    Prev
    Next
    INDEX
    Explanations

    sports matches

    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
     Riy
    -0.08
    å®°
    -0.08
    WithTitle
    -0.08
    çĹħçĹĩ
    -0.08
     dere
    -0.08
    åŃĹ
    -0.08
    lit
    -0.08
    light
    -0.08
     pen
    -0.08
    _MESH
    -0.08
    POSITIVE LOGITS
    ä¹ĭäºī
    0.10
    ç»ĪçĶŁ
    0.09
    åĪ«çļĦ
    0.09
    .opensource
    0.09
    èĪ¹ä¸Ĭ
    0.09
    诸å¦Ĥ
    0.09
    åħ¶ä½Ļ
    0.09
    èį¥
    0.09
    èľ·
    0.09
    å·¥ä½ľç«Ļ
    0.09
    Activations Density 0.179%

    No Known Activations