© 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. 57136
    Prev
    Next
    INDEX
    Explanations

    flat materials like boards and panels

    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
    æĿĨ
    -0.11
    æ¡
    -0.11
    æłĩçļĦ
    -0.10
    ç®Ĺ
    -0.10
    棵æłij
    -0.09
    ç§Ĩ
    -0.09
    纡
    -0.09
    å¤ĸåľ°
    -0.09
    éħ±æ²¹
    -0.09
    æįŁä¼¤
    -0.08
    POSITIVE LOGITS
    çīĩ
    0.11
    à¹ģà¸ľ
    0.11
    æİĢèµ·
    0.11
    ä¸įæŃ»
    0.10
    edom
    0.10
    å¹ħ
    0.10
    çķ
    0.10
     Ấ
    0.10
    aping
    0.10
    å¼Ģæ°´
    0.09
    Activations Density 0.070%

    No Known Activations