© 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. 61186
    Prev
    Next
    INDEX
    Explanations

    happily

    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
     laz
    -0.10
    æł·çļĦ
    -0.10
    è§Ī
    -0.09
    prus
    -0.09
    ãģĦãģŁ
    -0.09
    à¸IJ
    -0.09
    lands
    -0.09
    è¶ģ
    -0.09
    æIJĶ
    -0.09
    彧
    -0.09
    POSITIVE LOGITS
    èı©
    0.09
    atively
    0.09
    alar
    0.09
    æ°¸è¿ľ
    0.09
    å¾Ģ
    0.09
    çĶ¨è½¦
    0.08
    äºĴ
    0.08
    Æ°
    0.08
    ahir
    0.08
    大æī¹
    0.08
    Activations Density 0.002%

    No Known Activations