© 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. 19252
    Prev
    Next
    INDEX
    Explanations

    served from

    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
    ombo
    -0.10
    rego
    -0.09
    è°ģèĥ½
    -0.09
    è¡ĮåĬ¨è®¡åĪĴ
    -0.09
    æľįåĬ¡è´¨éĩı
    -0.09
    armed
    -0.08
    æĪij们è¦ģ
    -0.08
    éĴĹ
    -0.08
    ystack
    -0.08
    Vect
    -0.08
    POSITIVE LOGITS
    illet
    0.12
    illance
    0.12
    icios
    0.11
    èĩ¾
    0.10
    ience
    0.10
    æĢģ度
    0.09
    icer
    0.09
    piece
    0.09
    èĨº
    0.09
    ices
    0.09
    Activations Density 0.071%

    No Known Activations