© 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. 35228
    Prev
    Next
    INDEX
    Explanations

    called or referred to

    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
    ç¡®
    -0.10
    KÄ°
    -0.09
    åIJĮæł·
    -0.09
    vice
    -0.09
    айл
    -0.09
    anka
    -0.09
    çIJ¦
    -0.08
    ä¸įå¿į
    -0.08
    à¸ķà¸Ļ
    -0.08
    NR
    -0.08
    POSITIVE LOGITS
    æľ¯è¯Ń
    0.10
    åı«åģļ
    0.10
     Mara
    0.09
    æ²Ĩ
    0.09
    å½Ĵ
    0.09
    apr
    0.09
    éķ¿å¤§
    0.09
    oras
    0.09
    港澳
    0.09
    orum
    0.08
    Activations Density 0.072%

    No Known Activations