© 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. 10297
    Prev
    Next
    INDEX
    Explanations

    or contact

    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
    çĩ®
    -0.09
    uzz
    -0.08
    sterdam
    -0.08
    大åºĨ
    -0.08
    ickerView
    -0.08
    糧
    -0.08
    èĺ§
    -0.08
    istol
    -0.08
    çļĤ
    -0.08
    .heroku
    -0.07
    POSITIVE LOGITS
    èݹ
    0.11
     nearest
    0.10
    åĽ¢
    0.10
    ä¸Ģä½į
    0.10
    æĿĥå¨ģ
    0.09
    åijĪ
    0.09
    å½ĵåľ°æĶ¿åºľ
    0.09
    åIJĦä½į
    0.09
    ome
    0.09
    ä¸įå¿ħè¦ģçļĦ
    0.08
    Activations Density 0.030%

    No Known Activations