© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21612
    Prev
    Next
    INDEX
    Explanations

    mate selection and mating relationships

    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
    à¹Į
    -0.10
    itzer
    -0.10
    tron
    -0.09
    оÑģÑĮ
    -0.09
    teen
    -0.09
    ย
    -0.09
    aston
    -0.09
    ög
    -0.09
    aceous
    -0.09
    orse
    -0.08
    POSITIVE LOGITS
    iliar
    0.15
    们çļĦ
    0.11
    volent
    0.10
    tribute
    0.10
    iei
    0.10
    mates
    0.10
    usz
    0.09
    ility
    0.09
     dục
    0.09
    geber
    0.09
    Activations Density 0.012%

    No Known Activations