© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52385
    Prev
    Next
    INDEX
    Explanations

    copyright notices and ownership

    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
    licate
    -0.09
    central
    -0.08
    çİĭèĢħ
    -0.08
     ÄijÆ°Æ¡ng
    -0.08
    大åŀĭ
    -0.08
    dee
    -0.08
    éªļ
    -0.08
    ical
    -0.08
    æ³ķè§Ħ
    -0.08
    å®Į
    -0.08
    POSITIVE LOGITS
    è¹²
    0.10
    OWNER
    0.10
    ëĪĦ
    0.09
    бел
    0.09
     OWNER
    0.09
    illions
    0.09
    对该
    0.08
    主人
    0.08
    ivative
    0.08
    åľ¨éĩĮéĿ¢
    0.08
    Activations Density 0.083%

    No Known Activations