© 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. 32174
    Prev
    Next
    INDEX
    Explanations

    obsolete or unsupported status

    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
    第ä¸Ģ次
    -0.10
    æīįå¹²
    -0.10
    olon
    -0.09
    èģ
    -0.09
    èģª
    -0.09
    åĪĿ次
    -0.08
     MAD
    -0.08
    ç½²
    -0.08
    åİŁæłĩé¢ĺ
    -0.08
     first
    -0.08
    POSITIVE LOGITS
    ä¸įåĨį
    0.12
    æ·ĺæ±°
    0.11
    obsolete
    0.10
     discontinued
    0.10
    èĥĮä¸Ĭ
    0.10
    è¡°éĢĢ
    0.10
    è¶ĭ
    0.10
     obsolete
    0.09
    åģľæŃ¢
    0.09
    èĢģæŧ
    0.09
    Activations Density 0.233%

    No Known Activations