© 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. 50896
    Prev
    Next
    INDEX
    Explanations

    academic program requirements

    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
    åĵªæĢķæĺ¯
    -0.10
    åıªèĥ½è¯´
    -0.09
    ATTER
    -0.09
    ű
    -0.09
    tures
    -0.08
    å½ĵçĦ¶æĺ¯
    -0.08
    ä¹ĭåĬ¿
    -0.08
     ked
    -0.08
    æĻļæĬ¥
    -0.08
    apore
    -0.08
    POSITIVE LOGITS
    aska
    0.09
    åįģä¸ĥ
    0.09
    LETE
    0.09
    æ¯ĽåŃĶ
    0.08
    æīĵåį¡
    0.08
    lete
    0.08
    ä¸įè¡Į
    0.08
    .sav
    0.08
    .gc
    0.08
    åĮĹ大
    0.08
    Activations Density 0.021%

    No Known Activations