© 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. 33502
    Prev
    Next
    INDEX
    Explanations

    terms, conditions, principles, rules, values

    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
     Freeze
    -0.09
    issor
    -0.09
    ç«¥è¯Ŀ
    -0.09
    çľī
    -0.08
    ä¸ĢèĦļ
    -0.08
     ISSN
    -0.08
    èĽ¾
    -0.08
    uto
    -0.08
     zwiÄħz
    -0.08
    ISS
    -0.08
    POSITIVE LOGITS
    HCI
    0.09
    пиÑģан
    0.09
    åĴĮæĬĢæľ¯
    0.09
    ãĥĬãĥ³
    0.09
    åĬŀäºĭ
    0.08
    å¤ĩ
    0.08
     делаÑĤÑĮ
    0.08
    ertiary
    0.08
     Rodney
    0.08
    ÙĬÙĥ
    0.08
    Activations Density 0.034%

    No Known Activations