© 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. 4994
    Prev
    Next
    INDEX
    Explanations

    merchandise and items

    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
    itud
    -0.09
    itudes
    -0.09
    寺
    -0.09
    /she
    -0.09
    unded
    -0.09
    åĶ¯
    -0.09
    åIJĪéĢĤ
    -0.08
     ver
    -0.08
    ish
    -0.08
    ikki
    -0.08
    POSITIVE LOGITS
    arian
    0.10
    éģĵåħ·
    0.10
    ÙĬض
    0.10
     Catalyst
    0.09
    ç¼Ĥ
    0.09
    affer
    0.08
    alin
    0.08
    cing
    0.08
    estr
    0.08
     Gri
    0.08
    Activations Density 0.007%

    No Known Activations