© 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. 11742
    Prev
    Next
    INDEX
    Explanations

    photographing and recording events

    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
    ä¿Ŀå®Ī
    -0.10
    extr
    -0.09
    ä¸ĢèĦļ
    -0.09
    æīĺ管
    -0.09
    åıªèĥ½è¯´
    -0.09
    ä¸ĬçıŃ
    -0.09
    丧
    -0.09
    楼å±Ĥ
    -0.09
    æĪĴ
    -0.08
    éħį
    -0.08
    POSITIVE LOGITS
    è®°å½ķ
    0.19
    æįķæįī
    0.17
    纪å½ķ
    0.16
    å½ķéŁ³
    0.16
     recording
    0.16
    å½ķåĪ¶
    0.16
     RECORD
    0.16
    æijĦåĥı
    0.15
     recordings
    0.15
    å½ķ
    0.15
    Activations Density 0.150%

    No Known Activations