© 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. 3997
    Prev
    Next
    INDEX
    Explanations

    ocular segment and lens

    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
    éªijè¡Į
    -0.10
    è¾ĵç»Ļ
    -0.09
    ä¸ĢåĪĻ
    -0.09
    çľ¼çķĮ
    -0.09
    è§ĨåĬĽ
    -0.09
    妾
    -0.09
    ä¸Ģçľ¼
    -0.08
    鸳
    -0.08
    åį°è±¡
    -0.08
     Byron
    -0.08
    POSITIVE LOGITS
    åħ»èĢģéĩij
    0.09
    INLINE
    0.08
    arrant
    0.08
     má»Ļ
    0.08
    æĪª
    0.08
    èĥļ
    0.08
    ension
    0.08
     unfold
    0.08
    _Context
    0.08
    ContentSize
    0.08
    Activations Density 0.208%

    No Known Activations