© 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. 56137
    Prev
    Next
    INDEX
    Explanations

    valley of tears

    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
    夷
    -0.11
    èĻļ
    -0.10
    æ¹Ľ
    -0.09
    æĿĢ人
    -0.09
    radi
    -0.09
    èĻĽ
    -0.09
    æĩĤäºĭ
    -0.09
    åĿ¦
    -0.09
    protocols
    -0.08
    çİ©ç¬ij
    -0.08
    POSITIVE LOGITS
    æľªçŁ¥
    0.10
     жизни
    0.09
    -mort
    0.08
    год
    0.08
    èĦĨ
    0.08
     Fischer
    0.08
    åīįéĢĶ
    0.08
    anus
    0.08
     mortal
    0.08
    craft
    0.08
    Activations Density 0.041%

    No Known Activations