© 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. 37635
    Prev
    Next
    INDEX
    Explanations

    HD quality video resolution

    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
    åĪ°ä½į
    -0.09
    æĸĩåĮĸèīºæľ¯
    -0.09
    WebRequest
    -0.09
    å¼±çĤ¹
    -0.08
     cub
    -0.08
    .hashCode
    -0.08
    æĶ¶
    -0.08
    è¯Ħå®ļ
    -0.08
    å¾Īå¥½åľ°
    -0.08
    arti
    -0.08
    POSITIVE LOGITS
    éĢ¼
    0.14
    é«ĺæ¸ħ
    0.13
    æ¸ħæĻ°
    0.11
    ç«ĭä½ĵ
    0.10
     Morales
    0.10
    ç²¾ç¾İ
    0.10
    裸
    0.10
    é¾ĻéŨ
    0.10
     resolution
    0.09
    ä¹İ
    0.09
    Activations Density 0.110%

    No Known Activations