© 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. 10668
    Prev
    Next
    INDEX
    Explanations

    " is the" or "{"

    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
    人å±ħ
    -0.11
    æķĸ
    -0.11
    OptionsResolver
    -0.10
    PropertyParams
    -0.10
    styleType
    -0.09
    oyer
    -0.09
    TypeDef
    -0.09
    ÙĦØ·
    -0.09
    å²ĺ
    -0.09
    _LVL
    -0.09
    POSITIVE LOGITS
    '
    0.09
    ...
    0.09
    åİĨåı²ä¸Ĭ
    0.08
    ä»įæľª
    0.08
    ...↵↵
    0.08
    1
    0.08
    CN
    0.08
    -
    0.08
     r
    0.08
    spacer
    0.07
    Activations Density 0.299%

    No Known Activations