© 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. 48457
    Prev
    Next
    INDEX
    Explanations

    attributed 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
    çĶ¸
    -0.10
    rio
    -0.09
    -handed
    -0.09
    ers
    -0.09
    衬
    -0.09
    .Dependency
    -0.09
    nings
    -0.08
    ÑĦоÑĢ
    -0.08
    oe
    -0.08
    rie
    -0.08
    POSITIVE LOGITS
    не
    0.09
    oller
    0.09
    èĢĺ
    0.08
    è£
    0.08
    uby
    0.08
    累累
    0.08
    IBUT
    0.08
    ains
    0.08
    åĪ°è´¦
    0.08
     даннÑĭм
    0.08
    Activations Density 0.014%

    No Known Activations