© 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. 35492
    Prev
    Next
    INDEX
    Explanations

    named driver

    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
    天涯
    -0.10
    æī®
    -0.09
    idge
    -0.09
    婳
    -0.08
     Nunes
    -0.08
    idos
    -0.08
    ä¸įå¦Ĥ
    -0.08
    伸åĩº
    -0.08
     Hat
    -0.08
    æģ¶
    -0.08
    POSITIVE LOGITS
    å¿ĥæĻº
    0.09
    ä¸ī家
    0.09
    Wilson
    0.09
    hill
    0.08
     Wilson
    0.08
     è¾ĵ
    0.08
    å¥ĸåѦéĩij
    0.08
    uent
    0.08
    ç»ĵæŀĦè°ĥæķ´
    0.08
     «
    0.08
    Activations Density 0.026%

    No Known Activations