© 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. 6524
    Prev
    Next
    INDEX
    Explanations

    circuitry

    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
    ðŁı»
    -0.14
    cheap
    -0.10
    ðŁı¼
    -0.10
    ision
    -0.09
    æĸ«
    -0.09
    å¢ĥ
    -0.09
    enu
    -0.09
    atory
    -0.09
    åīįæīĢ
    -0.09
    æ´ĹåĩĢ
    -0.09
    POSITIVE LOGITS
    ry
    0.16
    ronics
    0.11
    eer
    0.11
    ting
    0.11
    ally
    0.10
     breaker
    0.10
    tes
    0.10
    tle
    0.10
    matic
    0.10
    ries
    0.10
    Activations Density 0.049%

    No Known Activations