© 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. 38028
    Prev
    Next
    INDEX
    Explanations

    punctuation delimiting clauses

    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
    åĴĮå®ĮåĸĦ
    -0.11
    inand
    -0.10
    å¥ļ
    -0.09
    æĢ§åĴĮ
    -0.09
    å¾¼
    -0.09
    é«»
    -0.09
    ustin
    -0.09
    áz
    -0.09
    å¼ĢèĬ±
    -0.08
    æ³ķè§Ħ
    -0.08
    POSITIVE LOGITS
    thing
    0.09
    ละ
    0.08
    ocha
    0.08
     likely
    0.08
    unch
    0.08
    crease
    0.08
    åł´åIJĪãģ«ãģ¯
    0.07
    .Alter
    0.07
     of
    0.07
    .native
    0.07
    Activations Density 0.192%

    No Known Activations