© 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. 61417
    Prev
    Next
    INDEX
    Explanations

    code separator or definition

    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
    ä¸İåħ¶
    -0.08
    å¾ĹäºĨ
    -0.08
    åľ¨å¤ĸ
    -0.08
    çµ±
    -0.08
     gem
    -0.08
    åĶ¿
    -0.07
     intel
    -0.07
    oder
    -0.07
    enti
    -0.07
    itter
    -0.07
    POSITIVE LOGITS
    parator
    0.10
    éĴľ
    0.10
    .gwt
    0.10
    elly
    0.09
    ampton
    0.09
    éĢļçŁ¥ä¹¦
    0.09
    è¯ķéªĮåĮº
    0.09
     spep
    0.09
    æĹłå¿§
    0.09
    dsp
    0.09
    Activations Density 0.226%

    No Known Activations