© 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. 61011
    Prev
    Next
    INDEX
    Explanations

    confidence that

    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
    çļĦé£İéĻ©
    -0.09
    bine
    -0.09
    æĶ¾åģĩ
    -0.08
    OrNull
    -0.08
     conven
    -0.08
    éªĪ
    -0.08
    å¹³åĩ¡
    -0.08
    çĦī
    -0.08
    éĻIJåĪ¶
    -0.08
    ifo
    -0.08
    POSITIVE LOGITS
    ä¸Ģå®ļèĥ½
    0.10
    ä¸įä¼ļæľī
    0.10
    غÙĪ
    0.09
    èĥ½çľĭåĩº
    0.09
    ä»ĸä¼ļ
    0.09
    atica
    0.09
    олод
    0.09
    åħ´æĹº
    0.09
    èĥľä»»
    0.09
    åľ¨æľªæĿ¥
    0.09
    Activations Density 0.017%

    No Known Activations