© 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. 30325
    Prev
    Next
    INDEX
    Explanations

    tears and related concepts

    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
    ty
    -0.10
    åijĺ
    -0.09
    æĢĿæĥ³
    -0.09
    ton
    -0.09
    ration
    -0.08
    tl
    -0.08
    verted
    -0.08
     anc
    -0.08
    ert
    -0.08
    hr
    -0.08
    POSITIVE LOGITS
    çĹķ
    0.12
    LESS
    0.10
    beck
    0.10
    çıł
    0.10
    æ¶Ł
    0.10
    lessly
    0.10
    conditionally
    0.09
    æĤ¬æµ®
    0.09
    ful
    0.09
    initely
    0.09
    Activations Density 0.006%

    No Known Activations