© 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. 27127
    Prev
    Next
    INDEX
    Explanations

    disclaimers of warranties

    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
    èģĮ
    -0.10
    opoulos
    -0.10
    æ·³
    -0.09
    èµ°åIJij
    -0.09
    éªĦ
    -0.08
     INLINE
    -0.08
     walker
    -0.08
    è°¦
    -0.08
    åĽŀæĬ¥
    -0.08
     Marriott
    -0.08
    POSITIVE LOGITS
    ria
    0.10
    éĿŀè¦ģ
    0.10
    æīĢè°ĵ
    0.10
    çľīæ¯Ľ
    0.09
    ä¹°
    0.09
    /ws
    0.09
    褰
    0.09
    ues
    0.09
    ernel
    0.09
    FIT
    0.09
    Activations Density 0.496%

    No Known Activations