© 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. 23810
    Prev
    Next
    INDEX
    Explanations

    integral part of

    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
    scape
    -0.09
    bery
    -0.08
    iken
    -0.08
    rema
    -0.08
    sut
    -0.08
    imus
    -0.07
    åįĹéĥ¨
    -0.07
     запиÑģи
    -0.07
    忽çĦ¶
    -0.07
    ienza
    -0.07
    POSITIVE LOGITS
    mente
    0.12
    ity
    0.12
     minded
    0.11
    -minded
    0.11
    ité
    0.10
    ITY
    0.10
     обÑĢазом
    0.10
    ment
    0.10
    ä¸ĭä¸Ģ代
    0.10
    缸è¿ŀ
    0.10
    Activations Density 0.015%

    No Known Activations