© 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. 53420
    Prev
    Next
    INDEX
    Explanations

    did not know how

    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
    à¹Ģà¸Ħ
    -0.09
    _PRESENT
    -0.09
    çīł
    -0.09
    ivation
    -0.09
    许å¤ļ人
    -0.08
     MERCHANTABILITY
    -0.08
    بØŃ
    -0.08
    è¡¡
    -0.08
    uario
    -0.08
    æĽ´æĺ¯
    -0.08
    POSITIVE LOGITS
    稽
    0.09
    æ¦Ľ
    0.08
    æ£Ģ
    0.08
    ãģŀ
    0.08
    对æѤ
    0.08
    éĤ£ç§į
    0.08
    chap
    0.08
    ãĤ·ãĥ³ãĥĹãĥ«
    0.08
    abe
    0.08
    ünde
    0.08
    Activations Density 0.003%

    No Known Activations