© 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. 61757
    Prev
    Next
    INDEX
    Explanations

    ib followed by certain words

    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
    illed
    -0.11
    anton
    -0.09
    æĪij以为
    -0.09
    íį¼
    -0.09
    æľ¬ç½ij
    -0.09
     إذ
    -0.09
    edList
    -0.09
    æĦıè¯ĨåĪ°
    -0.09
    astr
    -0.08
    便äºİ
    -0.08
    POSITIVE LOGITS
    rary
    0.13
    0.10
    uilder
    0.10
    ternal
    0.09
    arms
    0.09
    wald
    0.08
     мн
    0.08
    teenth
    0.08
    æ®
    0.08
    ushi
    0.08
    Activations Density 0.049%

    No Known Activations