© 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. 61927
    Prev
    Next
    INDEX
    Explanations

    borders and lines

    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
    ä¸ĭéĿ¢å°±
    -0.10
    å¿ĥè¡Ģ
    -0.09
    æİ¥çĿĢ
    -0.09
    доб
    -0.09
    akov
    -0.09
    пиÑĤ
    -0.09
    è°·
    -0.09
    _PRI
    -0.09
    棺
    -0.09
    èĢ¿
    -0.08
    POSITIVE LOGITS
    çĹķ迹
    0.10
     borders
    0.10
    æĿ¡
    0.10
     Seam
    0.09
    纵横
    0.09
    edes
    0.08
    çijķçĸµ
    0.08
    zÄĻ
    0.08
    sidebar
    0.08
    å½ĵçĦ¶æĺ¯
    0.08
    Activations Density 0.164%

    No Known Activations