© 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. 34767
    Prev
    Next
    INDEX
    Explanations

    technical field or present invention

    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
    .IGNORE
    -0.08
    ogie
    -0.07
    LESS
    -0.07
    çĨŁ
    -0.07
    æĩ
    -0.07
    ä¸Ģæ³¢
    -0.07
    æĴķ
    -0.07
    åĽĽå¤Ħ
    -0.07
    å°¤åħ¶æĺ¯
    -0.07
    OOT
    -0.07
    POSITIVE LOGITS
    æĿ¡
    0.10
    笺
    0.09
    ä¸įå¾Ĺ
    0.09
    该åİ¿
    0.09
    ä¾Ľåħ»
    0.09
    æµ®åĬ¨
    0.09
    _BLE
    0.08
    irs
    0.08
    èįīæ¡Ī
    0.08
    ä»»ä½ķ人
    0.08
    Activations Density 0.064%

    No Known Activations