© 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. 23260
    Prev
    Next
    INDEX
    Explanations

    the accompanying materials

    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
    èŀŁ
    -0.09
    çķĻä¸ĭ
    -0.09
    ORT
    -0.08
    _super
    -0.08
    Exception
    -0.08
    åĢ¼å¾Ĺ
    -0.08
    ider
    -0.08
    çī¹åĪ«
    -0.08
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.08
    ocz
    -0.08
    POSITIVE LOGITS
    ило
    0.11
    çŃ¹å¤ĩ
    0.10
    æį¢äºĨ
    0.10
    elsen
    0.10
    anas
    0.10
    å¦ĤæĦı
    0.09
    梵
    0.09
    ãģķãģĦ
    0.09
    çĤ¼
    0.09
     multipart
    0.09
    Activations Density 0.007%

    No Known Activations