© 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. 21757
    Prev
    Next
    INDEX
    Explanations

    solvent bath vapor degreaser

    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
    佯
    -0.12
    çļĦé£Łçī©
    -0.11
    èķ
    -0.11
    å¤Ķ
    -0.11
    èĤī
    -0.10
    çĻ£
    -0.09
    æ®Ħ
    -0.09
    ont
    -0.09
    ijo
    -0.09
    失信
    -0.09
    POSITIVE LOGITS
     solvent
    0.13
    æĹı
    0.09
    å·¥
    0.09
    åĮĸå·¥
    0.09
    oved
    0.09
    溶
    0.09
    çĤĶ
    0.08
     chemistry
    0.08
    Sol
    0.08
    çķĻæĦı
    0.08
    Activations Density 0.093%

    No Known Activations