© 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. 32334
    Prev
    Next
    INDEX
    Explanations

    Columbus, Dispatch, Day, Crew

    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
    ube
    -0.10
    ivy
    -0.09
     Äijáo
    -0.09
    uum
    -0.09
    imal
    -0.09
     Rah
    -0.09
    ÑģÑĤв
    -0.09
    Ø·ÙĦاÙĤ
    -0.08
    ë¶Ħ
    -0.08
     Toll
    -0.08
    POSITIVE LOGITS
    arity
    0.11
    illo
    0.10
    鸱
    0.10
    anza
    0.10
    ings
    0.10
    agne
    0.09
    ForResult
    0.09
    AndPassword
    0.09
    éĿŀè¦ģ
    0.09
    éĿ¥
    0.09
    Activations Density 0.005%

    No Known Activations