© 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. 35256
    Prev
    Next
    INDEX
    Explanations

    algebraic

    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
    å¿¡
    -0.10
    åIJĮåŁİ
    -0.09
    adora
    -0.09
    поÑĩ
    -0.09
    ioned
    -0.09
    æ±
    -0.09
    IMUM
    -0.09
    stances
    -0.09
     Michaels
    -0.09
    obook
    -0.08
    POSITIVE LOGITS
    ic
    0.17
    ically
    0.10
    ÙĨÙĪ
    0.09
    mast
    0.09
     меÑģÑĤ
    0.09
     básica
    0.09
    æĿ¿åĿĹ
    0.08
    ighted
    0.08
    isor
    0.08
    onne
    0.08
    Activations Density 0.039%

    No Known Activations