© 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. 32927
    Prev
    Next
    INDEX
    Explanations

    drive partition management

    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¸įèĪį
    -0.09
     towels
    -0.09
    çīµ
    -0.09
    _horizontal
    -0.09
    常æĢģ
    -0.09
    è°Ĵ
    -0.09
    æĬ¬å¤´
    -0.09
    è°¯
    -0.09
    aley
    -0.09
    ç»®
    -0.09
    POSITIVE LOGITS
    partition
    0.08
    寸
    0.08
    çݰ身
    0.08
    æŀľ
    0.08
    èĤļ
    0.08
    0
    0.08
     explo
    0.08
    ette
    0.08
    5
    0.08
    erre
    0.08
    Activations Density 0.085%

    No Known Activations