© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53108
    Prev
    Next
    INDEX
    Explanations

    located

    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
    çĩİ
    -0.11
    éĩľ
    -0.10
    家ä¼Ļ
    -0.10
    å¹²éĥ¨
    -0.10
    åı«å£°
    -0.10
    èĪĤ
    -0.10
     multitude
    -0.09
    endas
    -0.09
    åĴĮæĶ¯æĮģ
    -0.09
    ç§ĺ书
    -0.09
    POSITIVE LOGITS
    åįģåĪĨéĩįè¦ģ
    0.09
    iles
    0.08
     part
    0.08
    èĢĮä¸Ķ
    0.08
    lys
    0.08
    棱
    0.08
    ä¸įæĸŃåľ°
    0.08
    ron
    0.08
    /is
    0.08
     therefore
    0.08
    Activations Density 0.096%

    No Known Activations