© 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. 31782
    Prev
    Next
    INDEX
    Explanations

    sacrifice

    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
     sorte
    -0.10
    set
    -0.10
    å®īåħ¨äºĭæķħ
    -0.09
    ÑģÑĤолÑĮ
    -0.09
    iers
    -0.08
    ifier
    -0.08
     ÑģамÑĭм
    -0.08
    ug
    -0.08
    ë¡Ŀ
    -0.08
    atabase
    -0.08
    POSITIVE LOGITS
     phẩm
    0.12
    äºĨä¸Ģ
    0.11
    åĵģ
    0.10
    illis
    0.09
    iego
    0.09
    allis
    0.09
    ми
    0.08
    游èīĩ
    0.08
    çĥ¨
    0.08
     readonly
    0.08
    Activations Density 0.004%

    No Known Activations