© 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. 23310
    Prev
    Next
    INDEX
    Explanations

    touchscreen display

    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
    åĴĮåľ°åĮº
    -0.10
    å½±
    -0.08
     Sung
    -0.08
    WORD
    -0.08
    åŀ
    -0.08
    تÙĪ
    -0.07
    ãĤĥ
    -0.07
    NA
    -0.07
    延误
    -0.07
    é«®
    -0.07
    POSITIVE LOGITS
    PIP
    0.10
    ©
    0.10
    iÄĻ
    0.09
    ety
    0.09
    _DP
    0.09
    åŃĶéĽĢ
    0.09
    çķĮéĿ¢
    0.09
    ìĬ¤íģ¬
    0.09
    交åıĭ
    0.08
    elly
    0.08
    Activations Density 0.023%

    No Known Activations