© 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. 10958
    Prev
    Next
    INDEX
    Explanations

    little, small, tiny things

    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
    æŃ»è§Ĵ
    -0.11
    æĶ¶åıĸ
    -0.10
    éªħ
    -0.09
    æĪŁ
    -0.09
    èĨ³
    -0.09
    .requires
    -0.09
    Touch
    -0.09
    åĨ¤
    -0.09
    æĽ¹æĵį
    -0.08
    åĽ½æľīèµĦ产
    -0.08
    POSITIVE LOGITS
     hall
    0.10
    vince
    0.09
    ä¸Ģæľ¬
    0.09
    iculty
    0.09
    åİħ
    0.08
    vro
    0.08
    elite
    0.08
    pcodes
    0.08
    éģ
    0.08
     Revenge
    0.08
    Activations Density 0.036%

    No Known Activations