© 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. 6915
    Prev
    Next
    INDEX
    Explanations

    normally

    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
    -0.12
    er
    -0.10
    vant
    -0.09
    zelf
    -0.09
    ifying
    -0.09
    éļľ
    -0.09
    æľªå¿ħ
    -0.08
    owing
    -0.08
    è¤Ĭ
    -0.08
    ified
    -0.08
    POSITIVE LOGITS
    heel
    0.11
     xuyên
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.10
    elia
    0.10
    æĥħåĨµä¸ĭ
    0.10
    æĿ¡ä»¶ä¸ĭ
    0.10
    ities
    0.09
    LocalizedString
    0.09
    çĬĬ
    0.09
    unist
    0.09
    Activations Density 0.021%

    No Known Activations