© 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. 57347
    Prev
    Next
    INDEX
    Explanations

    proximity to objects or places

    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
    åĮħ容
    -0.10
    åIJ¬å®Į
    -0.09
    ä¸Ģå®ļç¨ĭ度
    -0.09
    ìľ¤
    -0.09
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.09
    çıł
    -0.09
    èĬ¡
    -0.08
    æĪijä¸Ģ缴
    -0.08
    æŁ¯
    -0.08
    ower
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķ
    0.09
    æľīä»»ä½ķ
    0.09
    è·ĭ
    0.09
    åĮ¹
    0.09
    _FUN
    0.08
    ä»»ä½ķå½¢å¼ı
    0.08
    /fs
    0.08
    æĺĵ
    0.08
    inger
    0.08
    atz
    0.08
    Activations Density 0.026%

    No Known Activations