© 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. 4896
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions

    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
    Descriptor
    -0.09
     descriptor
    -0.08
     Descriptor
    -0.08
    åĨįä¹Łä¸į
    -0.08
    o
    -0.08
    ä¸įçĶ±
    -0.08
    åıijçİ°äºĨ
    -0.08
    ä¸įåĨį
    -0.08
    ch
    -0.08
    adm
    -0.08
    POSITIVE LOGITS
    xBD
    0.10
    pedo
    0.10
    PTY
    0.10
    çķ¢ç«Ł
    0.10
    ODB
    0.09
    qli
    0.09
    è¿ĩäºİ
    0.09
    æ¯ķç«Ł
    0.09
    uvw
    0.09
    à¹Ģร
    0.09
    Activations Density 0.079%

    No Known Activations