© 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. 27285
    Prev
    Next
    INDEX
    Explanations

    election results, medical terms, food/ingredients, catalyst, demographics

    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
    éĤ£æ®µ
    -0.10
    è¿Ļæł·ä¸Ģ个
    -0.09
    éĴī
    -0.09
    .rem
    -0.09
    诸å¦Ĥ
    -0.08
    å®ĥçļĦ
    -0.08
    gal
    -0.08
    åıĪæľī
    -0.08
    åħ¸åŀĭ
    -0.08
    .CONT
    -0.08
    POSITIVE LOGITS
    FINITY
    0.10
    ä¸Ńæĸ°
    0.10
    uite
    0.10
     BITS
    0.10
    æĸĩåĮĸèĬĤ
    0.09
    ê²°
    0.09
    _DX
    0.09
    .TestCase
    0.09
    ailable
    0.09
    çĶ«
    0.09
    Activations Density 0.010%

    No Known Activations