© 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. 18555
    Prev
    Next
    INDEX
    Explanations

    Enron, EnronOnline, etc

    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
    ç»Ħ
    -0.09
    _sensitive
    -0.09
    asmus
    -0.08
     GPLv
    -0.08
    ogs
    -0.08
    æĭĵ
    -0.08
    atters
    -0.08
    è¯Ĩ
    -0.08
    TOOLS
    -0.08
    /display
    -0.08
    POSITIVE LOGITS
    éĿ¥
    0.10
    奢
    0.09
    åĢĴéĹŃ
    0.09
    è¦ģ说
    0.09
    å·¢
    0.08
    éĢĥè·ij
    0.08
    贪婪
    0.08
    ä¸įæŃ»
    0.08
    åĽ°å¢ĥ
    0.08
    å¤Ħå¢ĥ
    0.08
    Activations Density 0.036%

    No Known Activations