© 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. 19337
    Prev
    Next
    INDEX
    Explanations

    loss of consciousness or responsiveness

    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
    ething
    -0.10
    çļ®èĤ¤çĹħ
    -0.10
    å¥ij
    -0.09
    åIJĥè¿ĩ
    -0.09
    è£ĺ
    -0.09
    æĥ³æī¾
    -0.09
    æĪ¾
    -0.08
    åķIJ
    -0.08
    ched
    -0.08
    obox
    -0.08
    POSITIVE LOGITS
    æĺı
    0.19
    æĻķ
    0.18
    æĺıè¿·
    0.17
    çľ©
    0.12
    æļ
    0.11
    éĨī
    0.11
    éĨĴæĿ¥
    0.11
     faint
    0.10
    æ¸ħéĨĴ
    0.10
    è¿Ń
    0.10
    Activations Density 0.105%

    No Known Activations