© 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. 9817
    Prev
    Next
    INDEX
    Explanations

    puppet or puppeteer

    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
    ¯
    -0.11
    ä½ĵè´´
    -0.10
    odox
    -0.10
    adays
    -0.09
    çļĦåģļæ³ķ
    -0.09
    æĥ¦
    -0.09
    izens
    -0.09
    çļĦ缮åħī
    -0.08
    å¾ħéģĩ
    -0.08
    ìĤ¬íķŃ
    -0.08
    POSITIVE LOGITS
    eer
    0.14
     Ñģобой
    0.12
    ../../../
    0.11
    ito
    0.10
    å¯IJ
    0.10
    åĦ¡
    0.10
    itos
    0.09
    een
    0.09
    ees
    0.09
    .scalar
    0.09
    Activations Density 0.006%

    No Known Activations