© 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. 11497
    Prev
    Next
    INDEX
    Explanations

    serving sizes and measurements

    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
    areth
    -0.10
    ovsky
    -0.09
    æĤŁ
    -0.09
    íĴĢ
    -0.09
    æħĪæĤ²
    -0.08
    .timing
    -0.08
    DU
    -0.08
    timing
    -0.08
    æī¾åĪ°äºĨ
    -0.08
    ила
    -0.08
    POSITIVE LOGITS
    æīĢæīĢ
    0.11
    ä¸ĢåįĬ
    0.10
    丧
    0.10
    éĢĤéĩı
    0.09
    _SHADOW
    0.09
    éħį件
    0.09
    upro
    0.09
    ä¸İåħ¶
    0.09
     авÑĤом
    0.09
    çļĦçľ¼
    0.08
    Activations Density 0.024%

    No Known Activations