© 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. 10044
    Prev
    Next
    INDEX
    Explanations

    comedy plays and movies

    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
    èĻĶ
    -0.09
    logan
    -0.08
     loft
    -0.08
    çŁ³å®¶
    -0.08
    æİı
    -0.08
    å¼Ģè¾Ł
    -0.08
    _tb
    -0.08
    ä¼Ł
    -0.08
    çĬ¹è±«
    -0.08
    ç°Ł
    -0.08
    POSITIVE LOGITS
    è°ij
    0.12
    åĸľåī§
    0.11
    èĦļ
    0.10
    ictory
    0.10
    acts
    0.10
    欢
    0.09
    失è°ĥ
    0.09
    cap
    0.09
    .metamodel
    0.08
    çĶ·å¥³
    0.08
    Activations Density 0.080%

    No Known Activations