© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22102
    Prev
    Next
    INDEX
    Explanations

    tide, sand, rock, leaf, Minneapolis

    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
    éļıæĦı
    -0.10
    çĺª
    -0.09
    éĹŃ
    -0.09
    说æ³ķ
    -0.09
    ä¸Ģ款
    -0.09
    ç½Ĥ
    -0.09
    éĵį
    -0.09
    .Dispatcher
    -0.08
    è²Į
    -0.08
    åĢŁè´·
    -0.08
    POSITIVE LOGITS
     Tide
    0.09
    æ½®
    0.09
     pits
    0.08
    穹
    0.08
    丫
    0.08
    æ®ĭçķĻ
    0.08
     Sands
    0.08
     tide
    0.08
    AttributeValue
    0.08
    .border
    0.08
    Activations Density 0.064%

    No Known Activations