© 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. 62829
    Prev
    Next
    INDEX
    Explanations

    clear vision or visibility

    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
    äºĭä¸ļ
    -0.10
    ML
    -0.09
    é¢Ħå¤ĩ
    -0.09
    iva
    -0.09
    äºĭæ¥Ń
    -0.09
    çŃ¹åĪĴ
    -0.08
    å¼±
    -0.08
    æĪ¢
    -0.08
    IVA
    -0.08
     weak
    -0.08
    POSITIVE LOGITS
     visibility
    0.13
    visibility
    0.12
    æµĬ
    0.12
     Visibility
    0.12
    çľĭæ¸ħ
    0.12
    è§Ĩ线
    0.12
    éĽ¾
    0.11
    éĽ¾éľ¾
    0.11
    Visibility
    0.10
     fog
    0.10
    Activations Density 0.027%

    No Known Activations