© 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. 19436
    Prev
    Next
    INDEX
    Explanations

    Gym, PORT, Nations

    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
    çĮ¥
    -0.08
    åħ¨åijĺ
    -0.08
    ä¸Ĭç½ij
    -0.08
    çľĭå¾Ĺ
    -0.08
    çĿĽ
    -0.08
    èĪª
    -0.08
    ero
    -0.08
    è¢Ń
    -0.08
    çŃ¹éĽĨ
    -0.07
    ç«ĭ足
    -0.07
    POSITIVE LOGITS
    <LM
    0.10
    OLON
    0.10
    FilterWhere
    0.09
    âĸ¾
    0.09
    /apis
    0.09
    íĻĶ
    0.09
    lint
    0.09
    æ·ĺæ±°
    0.09
    doi
    0.09
    å±ħä½ı
    0.09
    Activations Density 0.071%

    No Known Activations