© 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. 6643
    Prev
    Next
    INDEX
    Explanations

    hood or parenthood

    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
    ations
    -0.11
    mond
    -0.10
    TING
    -0.10
    èľį
    -0.09
    onaut
    -0.09
    íģ¼
    -0.09
    åĪ°æľĢåIJİ
    -0.09
    侬
    -0.09
    å±Ģéķ¿
    -0.09
    ur
    -0.09
    POSITIVE LOGITS
    ridge
    0.13
    ie
    0.11
    ÙĦاÙĦ
    0.11
    town
    0.11
    ../../../
    0.11
    ened
    0.11
    ed
    0.10
    laces
    0.10
    ously
    0.10
    liner
    0.10
    Activations Density 0.014%

    No Known Activations