© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51419
    Prev
    Next
    INDEX
    Explanations

    water temperature

    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
    æĮ¥
    -0.09
    è§ģè¯Ĩ
    -0.09
    bez
    -0.09
    å¦Ĵ
    -0.09
    å«ī
    -0.08
     Jennings
    -0.08
    ç»ĪçĶŁ
    -0.08
    âĢĹ
    -0.08
    tÃł
    -0.08
    /resource
    -0.08
    POSITIVE LOGITS
    IOD
    0.08
    çĦIJ
    0.08
    åĩij
    0.08
    çĬ¯
    0.08
    çĥŃæ°´
    0.08
     Fallen
    0.08
    .vis
    0.08
    æľ
    0.08
    é¢Ħå¤ĩ
    0.08
    ç¨į
    0.08
    Activations Density 0.014%

    No Known Activations