© 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. 27593
    Prev
    Next
    INDEX
    Explanations

    don't negative

    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
    tings
    -0.11
    ãģĬé¡ĺãģĦ
    -0.09
    atten
    -0.09
    idel
    -0.09
    åķ¶
    -0.09
    éĢµ
    -0.09
    udio
    -0.09
    debian
    -0.09
    ä½ľèĢħæľ¬äºº
    -0.09
    aurant
    -0.09
    POSITIVE LOGITS
    er
    0.12
    é«®
    0.10
    hil
    0.10
    ÑģÑĥÑĤ
    0.10
    ers
    0.10
     ведÑĮ
    0.10
    czy
    0.09
    al
    0.09
    sig
    0.09
    и
    0.09
    Activations Density 0.087%

    No Known Activations