© 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. 58649
    Prev
    Next
    INDEX
    Explanations

    completely/fully followed by adjective

    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
    å»ĵ
    -0.09
    sie
    -0.09
    èĥ½åĬĽå¼º
    -0.09
    ãģĦãģŁãĤī
    -0.09
    裱
    -0.09
     FEATURES
    -0.08
    é«»
    -0.08
    æĦŁåħ´è¶£çļĦ
    -0.08
    å°ıå§IJ
    -0.08
    ç»°
    -0.08
    POSITIVE LOGITS
    åħ¨ç¨ĭ
    0.11
    å®Įåħ¨æĺ¯
    0.10
    æŶéĻIJ
    0.09
    åIJij举
    0.09
    cken
    0.08
    Parm
    0.08
    课å¤ĸ
    0.08
    pare
    0.08
    ells
    0.08
    ä¸İæĹ¶ä¿±
    0.08
    Activations Density 0.030%

    No Known Activations