© 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. 39226
    Prev
    Next
    INDEX
    Explanations

    joy and happiness

    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
    åĽŀäºĭ
    -0.09
    wers
    -0.09
    客æ°Ķ
    -0.09
    AW
    -0.08
    å°Ĭéĩį
    -0.08
    عد
    -0.08
    station
    -0.08
    å®ļäºĨ
    -0.08
    çļĦç¾İ好
    -0.08
    ол
    -0.08
    POSITIVE LOGITS
    fully
    0.15
    fulness
    0.11
    FUL
    0.10
    ful
    0.10
    åĽłä¸ºä»ĸ
    0.10
    mir
    0.09
    çªĿ
    0.09
    åĽłä¸ºä»ĸ们
    0.09
    椤
    0.09
     налиÑĩ
    0.09
    Activations Density 0.026%

    No Known Activations