© 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. 36520
    Prev
    Next
    INDEX
    Explanations

    certainty, truth, reality

    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
    妻
    -0.09
    ä¸ĩä¸Ģ
    -0.09
    ouri
    -0.08
    çļĦæĥħå½¢
    -0.08
    æ¹Ħ
    -0.08
    å¤ĩ
    -0.08
    ion
    -0.08
    èį¤
    -0.08
    pher
    -0.08
    é«ĺæĺĤ
    -0.08
    POSITIVE LOGITS
    èį·
    0.09
    _ALLOW
    0.09
    UMB
    0.09
    åı¯æĢľ
    0.09
    .dc
    0.08
    ANC
    0.08
     Pending
    0.08
    anke
    0.08
    æīĭèħķ
    0.08
    å¾ħ
    0.08
    Activations Density 0.028%

    No Known Activations