© 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. 16971
    Prev
    Next
    INDEX
    Explanations

    xs, XS, XD, xe, xi, l

    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
    и
    -0.11
    eter
    -0.10
    edList
    -0.09
    rim
    -0.09
    ching
    -0.09
    edImage
    -0.09
    roe
    -0.09
    áĥ¥
    -0.09
    ARDS
    -0.09
    æĬ¢éĻ©
    -0.09
    POSITIVE LOGITS
    unger
    0.11
    å¸Ļ
    0.09
    笼
    0.09
    森æŀĹåħ¬åĽŃ
    0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.09
    è¾£
    0.09
    ilos
    0.08
    çıĤ
    0.08
    sto
    0.08
    arious
    0.08
    Activations Density 0.172%

    No Known Activations