© 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. 27873
    Prev
    Next
    INDEX
    Explanations

    majority Leader or Opinion

    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
    æĢĢæĬ±
    -0.09
    çķ´
    -0.08
    arium
    -0.08
    izzo
    -0.08
    åīįæīĢ
    -0.08
    omics
    -0.08
    ä½ĵè´´
    -0.08
    iatric
    -0.08
    ä¸Ģè¶Ł
    -0.08
    gree
    -0.08
    POSITIVE LOGITS
    cy
    0.10
    ä¸įæĺİ
    0.10
    -feedback
    0.09
    nÃŃ
    0.09
    åĬĽéĩı
    0.09
    rag
    0.09
    semb
    0.09
    æľªå©ļ
    0.09
    æ¾Ħæ¸ħ
    0.09
    rush
    0.09
    Activations Density 0.013%

    No Known Activations