© 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. 10137
    Prev
    Next
    INDEX
    Explanations

    enological production

    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
    é£İåIJ¹
    -0.09
    èĮĤ
    -0.09
    bal
    -0.09
    éķľå¤´
    -0.08
    \Eloquent
    -0.08
    plex
    -0.08
    鹦
    -0.08
    为æĬĵ
    -0.08
    toy
    -0.08
    éĺī
    -0.08
    POSITIVE LOGITS
    è½±
    0.10
    æ±²
    0.09
    æĪIJæķĪ
    0.08
    ç´«èī²
    0.08
    èµĽ
    0.08
    æ¾Ħæ¸ħ
    0.08
     далÑĮн
    0.08
    è·ª
    0.08
    åħ«åį¦
    0.08
    åķĨä¸ļåĮĸ
    0.08
    Activations Density 0.180%

    No Known Activations