© 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. 39637
    Prev
    Next
    INDEX
    Explanations

    won or won't

    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
    usercontent
    -0.12
     воÑĤ
    -0.11
    dır
    -0.10
    _preference
    -0.10
    ãĥ³ãĤ°
    -0.10
    çĮĸ
    -0.09
    æĪij对
    -0.09
    printStats
    -0.09
    жа
    -0.09
     пÑĥнкÑĤ
    -0.09
    POSITIVE LOGITS
    est
    0.11
    ed
    0.11
    ä¸įèµ·
    0.11
    ãģ£ãģ±
    0.10
    imately
    0.09
    ay
    0.09
    ctor
    0.09
    ä¸įäºĨ
    0.09
    ’t
    0.09
    ãĤī
    0.09
    Activations Density 0.024%

    No Known Activations