© 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. 38729
    Prev
    Next
    INDEX
    Explanations

    familiar concepts or configurations

    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
    aceous
    -0.10
     Ek
    -0.09
    åŁºæľ¬æĥħåĨµ
    -0.09
    raph
    -0.09
    arella
    -0.09
    èĻº
    -0.08
    çĺ¾
    -0.08
    ä¸Ģ个æĺ¯
    -0.08
    身亡
    -0.08
    åªĴ
    -0.08
    POSITIVE LOGITS
    mente
    0.15
    iliar
    0.11
    åģļèµ·
    0.10
    SSION
    0.10
    nte
    0.09
    éĿ¢åŃĶ
    0.09
    åĴĮæĶ¯æĮģ
    0.09
    поÑĤ
    0.09
    ìĪĻ
    0.09
    thers
    0.09
    Activations Density 0.010%

    No Known Activations