© 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. 38245
    Prev
    Next
    INDEX
    Explanations

    . followed by capitalized words

    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
    ä¸ĭä¸Ģ
    -0.10
    è´µ
    -0.10
    azed
    -0.09
    åIJĪæ³ķ
    -0.09
    JUnit
    -0.08
    åħīæĺİ
    -0.08
    tent
    -0.08
     Lau
    -0.08
    ä¸įè¡Į
    -0.08
    nds
    -0.08
    POSITIVE LOGITS
    åIJİèĢħ
    0.10
    etti
    0.09
    .soft
    0.08
    å¨ĵ
    0.08
    arah
    0.08
     eup
    0.08
    ä¸įè´Ł
    0.07
    ãģĨãģ¡ãģ«
    0.07
    é£Ļ
    0.07
    orgen
    0.07
    Activations Density 0.506%

    No Known Activations