© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 322
    Prev
    Next
    INDEX
    Explanations

    microscopy and microscopes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    æįĨç»ij
    -0.28
    ç»ij
    -0.25
     Countdown
    -0.25
    代
    -0.24
    ÑĪиб
    -0.24
     withholding
    -0.24
     chute
    -0.24
    æ¶ĪèĢĹ
    -0.23
     дог
    -0.23
     season
    -0.23
    POSITIVE LOGITS
     microscope
    0.68
     microscopy
    0.60
     microscopic
    0.53
     specimen
    0.42
    å¾®è§Ĥ
    0.41
     specimens
    0.40
     photographs
    0.38
    è§Ģå¯Ł
    0.38
     images
    0.38
    _micro
    0.38
    Activations Density 0.188%

    No Known Activations