© 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. 30624
    Prev
    Next
    INDEX
    Explanations

    very 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
    лÑı
    -0.09
    ltra
    -0.09
    綦
    -0.09
    æĹ¶ä»£ä¸ŃåĽ½
    -0.08
    æľĢçĪ±
    -0.08
    gov
    -0.08
    elier
    -0.08
    CHAN
    -0.08
    EMU
    -0.08
    æĢ»ç®Ĺ
    -0.08
    POSITIVE LOGITS
    antly
    0.10
    æį§
    0.10
    æĬĬä»ĸ
    0.10
    åľ°ä¸Ń
    0.09
    çºłç»ĵ
    0.09
    éķ¿èĢģ
    0.09
    arias
    0.09
    çľĭä»ĸ
    0.09
    ant
    0.08
    èµ·æĿ¥
    0.08
    Activations Density 0.029%

    No Known Activations