© 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. 49688
    Prev
    Next
    INDEX
    Explanations

    Arundel County

    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
    天èĬ±
    -0.09
    ove
    -0.09
    ira
    -0.09
    ilden
    -0.08
    èĻŀ
    -0.08
    馨
    -0.08
    wyn
    -0.08
    Insets
    -0.08
    çĤĻ
    -0.07
    ÑĢаÑģÑĤ
    -0.07
    POSITIVE LOGITS
    ç»ıå¼Ģ
    0.12
    峡
    0.09
    ness
    0.09
    ä¸įåħį
    0.09
     BaseActivity
    0.09
    åı£å²¸
    0.09
    PerPage
    0.09
    Ñģад
    0.09
    æ´ĹåĩĢ
    0.09
    åĵªè£¡
    0.08
    Activations Density 0.002%

    No Known Activations