© 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. 8526
    Prev
    Next
    INDEX
    Explanations

    upgrade from or to

    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
    lessly
    -0.11
    est
    -0.10
    /or
    -0.09
    aceous
    -0.09
    uilder
    -0.09
    nest
    -0.09
    ness
    -0.09
    ĺ
    -0.09
    uka
    -0.09
    quets
    -0.09
    POSITIVE LOGITS
    /down
    0.11
    ging
    0.09
    OrCreate
    0.08
    abbr
    0.08
    неÑĨ
    0.08
    è¯ķéªĮåĮº
    0.08
    MENT
    0.08
    imate
    0.08
    æķ¦
    0.08
    manuel
    0.08
    Activations Density 0.017%

    No Known Activations