© 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. 21568
    Prev
    Next
    INDEX
    Explanations

    words starting with cro

    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
    urd
    -0.10
    itre
    -0.10
    eral
    -0.09
    uation
    -0.09
    åħħæ²Ľ
    -0.09
    ãĥ³ãĤ°
    -0.09
     пÑĢавилÑĮно
    -0.08
    END
    -0.08
    aneously
    -0.08
    ä½»
    -0.08
    POSITIVE LOGITS
    dfunding
    0.10
    codile
    0.10
    icle
    0.10
    bery
    0.10
    inality
    0.10
    ean
    0.09
    é¹ķ
    0.09
    pped
    0.09
    illon
    0.08
    ä¸įçĶ¨æĭħå¿ĥ
    0.08
    Activations Density 0.017%

    No Known Activations