© 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. 6465
    Prev
    Next
    INDEX
    Explanations

    aging

    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¸įä¸ĭ
    -0.12
     vej
    -0.09
    è¯Ĩ
    -0.09
    .Diff
    -0.09
    çĬį
    -0.09
    诱æĥij
    -0.09
    å¼Ģ头
    -0.09
    enne
    -0.08
    å½±
    -0.08
    /on
    -0.08
    POSITIVE LOGITS
    ãģĸ
    0.08
    梵
    0.08
    èݺ
    0.08
    åĴĮåıijå±ķ
    0.08
    Aware
    0.08
    jec
    0.08
    æĮĿ
    0.08
    -fashioned
    0.08
    ouch
    0.08
    è¿ĩç¨ĭä¸Ń
    0.08
    Activations Density 0.044%

    No Known Activations