© 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. 10484
    Prev
    Next
    INDEX
    Explanations

    journal names

    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
    å¾®
    -0.09
    çĶ¨äººåįķä½į
    -0.09
    BUR
    -0.09
    伸åĩº
    -0.09
    çĶ¨äºº
    -0.09
    rug
    -0.09
    ivid
    -0.09
    çªŁ
    -0.08
    stä
    -0.08
    ä¸įå¿ħè¦ģçļĦ
    -0.08
    POSITIVE LOGITS
     journal
    0.09
    åĦ¿å¥³
    0.09
    ournal
    0.09
    alcon
    0.09
     Journal
    0.09
    è§Ĭ
    0.09
    åĪijæ³ķ
    0.08
    eta
    0.08
    Journal
    0.08
    éĻIJé¢Ŀ
    0.08
    Activations Density 0.032%

    No Known Activations