© 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. 61649
    Prev
    Next
    INDEX
    Explanations

    defining aspects and implications

    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
    çģŀ
    -0.10
    utton
    -0.09
    phia
    -0.09
    åĬłä¸Ĭ
    -0.09
    legg
    -0.08
    perienced
    -0.08
    æĦıåĽ¾
    -0.08
    Invariant
    -0.08
    éro
    -0.08
    éĤł
    -0.08
    POSITIVE LOGITS
    /is
    0.10
    寤
    0.10
    å¾Ī强
    0.10
    ä¸į容
    0.09
    ä¸Ģå®ļçļĦ
    0.09
    夫
    0.09
    å¾Īé«ĺ
    0.09
    æ¶İ
    0.08
    绿水
    0.08
    çļĦå°±æĺ¯
    0.08
    Activations Density 0.283%

    No Known Activations