© 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. 61421
    Prev
    Next
    INDEX
    Explanations

    thank you much or lot

    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
    æŁ°
    -0.11
    æĭ¢
    -0.10
    æµĵåİļ
    -0.09
    çĴľ
    -0.09
    æĸ¯é¡¿
    -0.09
    åĮłå¿ĥ
    -0.09
    çĮĿ
    -0.09
    minster
    -0.09
    å¾ĪæŃ£å¸¸
    -0.09
    аниÑĨ
    -0.09
    POSITIVE LOGITS
    ingly
    0.10
    第ä¸ī个
    0.08
     Choir
    0.08
    FER
    0.08
    é»ĺ
    0.08
    WND
    0.08
    ered
    0.08
    ä¸ĵä¸ļçļĦ
    0.08
    åĵī
    0.08
    aea
    0.07
    Activations Density 0.007%

    No Known Activations