© 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. 17883
    Prev
    Next
    INDEX
    Explanations

    sports broadcasts and live updates

    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
    åĪĿä¸ī
    -0.09
    arts
    -0.09
    è¶ħæłĩ
    -0.09
    åºŁ
    -0.08
    é¢Ĩè¢ĸ
    -0.08
    ä½ķå¿ħ
    -0.08
    itemap
    -0.08
    åĽ¢åijĺ
    -0.08
    ?key
    -0.08
    åħ«åįģ
    -0.08
    POSITIVE LOGITS
    Coverage
    0.10
     Coverage
    0.10
     влад
    0.09
    çĭ¬å®¶
    0.09
    çĮ
    0.09
    çĶµè§Ĩ
    0.09
    bett
    0.09
    åĮħ
    0.09
    ä¼ī
    0.09
    LAY
    0.09
    Activations Density 0.170%

    No Known Activations