© 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. 35198
    Prev
    Next
    INDEX
    Explanations

    non-invasive procedures

    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
    zelf
    -0.09
    trust
    -0.09
    anut
    -0.09
     læ
    -0.08
    æĤłæĤł
    -0.08
    æ¡Ī
    -0.08
    oric
    -0.08
    使èĢħ
    -0.08
    usable
    -0.08
    èµĬ
    -0.08
    POSITIVE LOGITS
    æĢ§çļĦ
    0.10
    ness
    0.10
    UME
    0.10
    ible
    0.10
    iveness
    0.10
    ly
    0.10
    íķĺê²Į
    0.09
    ç¡Į
    0.09
    ities
    0.09
    åĿij
    0.09
    Activations Density 0.037%

    No Known Activations