© 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. 11028
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by 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
    对人ä½ĵ
    -0.10
    对
    -0.09
    å¯¹æľªæĿ¥
    -0.09
    zb
    -0.09
    _PREVIEW
    -0.08
    LAG
    -0.08
    GRA
    -0.08
    ldb
    -0.08
    rades
    -0.08
     physically
    -0.08
    POSITIVE LOGITS
    åıĬåħ¶
    0.12
    çĮ¿
    0.10
    åł°
    0.10
    жал
    0.09
    çī¹åĪ«æĺ¯
    0.09
    åıªèĥ½è¯´
    0.09
    å¼ĢèĬ±
    0.09
    çļĦåıijå±ķ
    0.09
    éĢģåĩº
    0.09
     Chambers
    0.09
    Activations Density 0.360%

    No Known Activations