© 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. 18823
    Prev
    Next
    INDEX
    Explanations

    Vienna and companies

    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
    Õ¦
    -0.09
    çĵ¢
    -0.09
    vc
    -0.09
    омеÑĢ
    -0.08
     CONDITIONS
    -0.08
    æĮ¥
    -0.08
    å¥Ĺè£ħ
    -0.08
    acies
    -0.08
    ouns
    -0.08
    èĸ®
    -0.08
    POSITIVE LOGITS
    uess
    0.11
    åĺŁ
    0.10
    士
    0.10
    ÙĬز
    0.09
    etur
    0.09
    خت
    0.09
    etta
    0.09
    ÙħÙĬÙĨ
    0.09
    群ä¼Ĺ
    0.09
    ieves
    0.09
    Activations Density 0.006%

    No Known Activations