© 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. 17772
    Prev
    Next
    INDEX
    Explanations

    such as

    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
    âĺĿ
    -0.08
    olume
    -0.08
    èĭĶ
    -0.08
    åIJĮæĹ¶ä¹Ł
    -0.08
    upo
    -0.08
    WRITE
    -0.08
    liner
    -0.08
    OX
    -0.08
    iny
    -0.08
    åĩij
    -0.08
    POSITIVE LOGITS
    /AP
    0.09
    å¿ĺè®°
    0.09
    /-
    0.09
    ÃŃc
    0.08
    .appspot
    0.08
     ÙĪجÙĩ
    0.08
    WithValue
    0.08
    夷
    0.08
    aign
    0.08
    itan
    0.08
    Activations Density 0.205%

    No Known Activations