© 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. 31681
    Prev
    Next
    INDEX
    Explanations

    resource providing or for

    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
    aket
    -0.09
    éĩijå±±
    -0.09
    å¾Ĵ
    -0.09
    roph
    -0.09
    hydr
    -0.08
    town
    -0.08
    çĤ¹åĩ»æŁ¥çľĭ
    -0.08
    æ¤į
    -0.08
     GRA
    -0.08
    tek
    -0.08
    POSITIVE LOGITS
    fulness
    0.14
    ful
    0.10
    hip
    0.10
    ÑıÑģÑĮ
    0.10
    à¸ĺรรม
    0.09
    åİ¢
    0.09
    åIJĦè¡Į
    0.09
    åIJĦåİ¿
    0.09
    æ¶ĪèĢĹ
    0.09
    heck
    0.09
    Activations Density 0.025%

    No Known Activations