© 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. 61517
    Prev
    Next
    INDEX
    Explanations

    solid

    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¿ĺ
    -0.09
    ç¦Ģ
    -0.09
    足迹
    -0.09
    ạn
    -0.08
    éķ¬
    -0.08
    ç¼ł
    -0.08
    èĴĮ
    -0.08
     tapes
    -0.08
    chool
    -0.08
    æĵ¦
    -0.08
    POSITIVE LOGITS
    åħīæ»ij
    0.12
    以èī²
    0.11
    -solid
    0.11
    纯
    0.10
    主ä¹īèĢħ
    0.10
    ÑIJ
    0.10
    _continuous
    0.10
    转载请
    0.10
     невоз
    0.09
    ä¸Ģä½ĵ
    0.09
    Activations Density 0.063%

    No Known Activations