© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52075
    Prev
    Next
    INDEX
    Explanations

    considered

    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
    rock
    -0.10
    itude
    -0.10
    busters
    -0.10
    ologies
    -0.10
    inally
    -0.09
    ey
    -0.09
     пÑĢоÑĨ
    -0.09
    guns
    -0.09
    inel
    -0.09
    roc
    -0.09
    POSITIVE LOGITS
    ately
    0.14
    ate
    0.11
    igar
    0.11
    SSION
    0.11
    ably
    0.10
    ered
    0.10
    ation
    0.10
    azioni
    0.09
    ationToken
    0.09
    avel
    0.09
    Activations Density 0.041%

    No Known Activations