© 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. 5283
    Prev
    Next
    INDEX
    Explanations

    proof and evidence

    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
    posables
    -0.09
    æģ£
    -0.09
    å§ĵ
    -0.09
    æĸ°å½¢åĬ¿
    -0.09
    aways
    -0.09
    abei
    -0.09
    èģĭ
    -0.09
    为é¦ĸ
    -0.09
    çľ¼çķĮ
    -0.09
    rush
    -0.08
    POSITIVE LOGITS
    è¯ģæĺİ
    0.24
    è¯ģæį®
    0.20
    è¯ģå®ŀ
    0.19
    èŃīæĺİ
    0.19
     proof
    0.17
     evidence
    0.17
     prove
    0.16
    èŃī
    0.16
    prove
    0.15
    è¯ģ
    0.15
    Activations Density 0.061%

    No Known Activations