© 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. 32696
    Prev
    Next
    INDEX
    Explanations

    to name a few

    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
    æĮĩ纹
    -0.11
    ointed
    -0.10
    вл
    -0.10
    ç½®æį¢
    -0.10
    gang
    -0.09
    æľīæķĪ
    -0.08
    -With
    -0.08
     Manson
    -0.08
    ä½»
    -0.08
     Straw
    -0.08
    POSITIVE LOGITS
    among
    0.09
     among
    0.09
    è°Ł
    0.08
    èļķ
    0.08
    çģ¼
    0.08
    å¤©åľ°
    0.08
    .loop
    0.08
    æĥ³åĪ°äºĨ
    0.08
    _SUS
    0.08
    æĸ¯åŁº
    0.08
    Activations Density 0.008%

    No Known Activations