© 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. 33319
    Prev
    Next
    INDEX
    Explanations

    obsolete, useless, or redundant

    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
    ceipt
    -0.11
    ÑĢÑı
    -0.10
    åģ¶
    -0.10
    ä»Ĺ
    -0.10
    æį¢
    -0.09
    ä½ļ
    -0.09
    è¿ŀéĶģ
    -0.09
    æıĽ
    -0.09
    æĶ¹
    -0.09
    é¢ĩæľī
    -0.09
    POSITIVE LOGITS
    å¤ļä½Ļ
    0.16
     obsolete
    0.15
    æ·ĺæ±°
    0.14
    没å¿ħè¦ģ
    0.13
     useless
    0.13
    å¤ļä½ĻçļĦ
    0.13
    ä¸įå¿ħ
    0.13
     redundant
    0.12
    ä¸įéľĢè¦ģ
    0.12
    åºŁ
    0.12
    Activations Density 0.079%

    No Known Activations