© 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. 54353
    Prev
    Next
    INDEX
    Explanations

    tighten, tighter, tightly

    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
    ä¿Ŀ
    -0.08
    .Manifest
    -0.08
     Verm
    -0.08
    éģĵåħ·
    -0.08
    éļľ
    -0.08
    åĪ¶åĨ·
    -0.08
    ç³Ĭ
    -0.08
    é¼İ
    -0.08
    æĭħ
    -0.08
    åĤ»
    -0.08
    POSITIVE LOGITS
    ç´§
    0.16
    tight
    0.16
     tight
    0.13
    ç´§å¯Ĩ
    0.13
     tighter
    0.12
    紧紧
    0.12
     Tight
    0.12
    ç·Ĭ
    0.12
    ç´§åĩij
    0.11
     tightly
    0.11
    Activations Density 0.034%

    No Known Activations