© 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. 40006
    Prev
    Next
    INDEX
    Explanations

    general + titles or names

    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
    prints
    -0.09
    uan
    -0.09
    çĶ¬
    -0.09
    enko
    -0.09
    atto
    -0.08
    inh
    -0.08
    agg
    -0.08
    unny
    -0.08
    ç²¥
    -0.08
    ward
    -0.08
    POSITIVE LOGITS
    mente
    0.17
    -purpose
    0.17
    ized
    0.14
    ÃŃsimo
    0.13
    ities
    0.13
    ised
    0.12
    ization
    0.12
    izable
    0.11
    itÃł
    0.11
    isateur
    0.11
    Activations Density 0.061%

    No Known Activations