© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50750
    Prev
    Next
    INDEX
    Explanations

    comparing and analyzing data

    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
    ulen
    -0.09
    icky
    -0.09
     curt
    -0.09
    为æĬĵ
    -0.09
     Ñģобой
    -0.08
    .pb
    -0.08
    apl
    -0.08
     pb
    -0.08
    å±ij
    -0.08
    å±ħçĦ¶
    -0.08
    POSITIVE LOGITS
     seen
    0.08
    èªī
    0.08
     Zucker
    0.08
    å¼ķé¢Ĩ
    0.08
    左侧
    0.08
    uni
    0.08
    acter
    0.08
    èĻ¬
    0.08
    å¾Ĺ以
    0.08
    ä¸Ńå¼ı
    0.08
    Activations Density 0.708%

    No Known Activations