© 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. 34106
    Prev
    Next
    INDEX
    Explanations

    printing, light, mechanical, electronic, camera

    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
    argo
    -0.10
    污水
    -0.09
    .guard
    -0.09
    åľ°åŁŁ
    -0.08
    /comment
    -0.08
    éĻ¡
    -0.08
     ÑĤеле
    -0.08
    agini
    -0.08
     Recomm
    -0.08
    æħķ
    -0.08
    POSITIVE LOGITS
    èªĬ
    0.11
    åĪ»
    0.10
    cket
    0.09
     SCI
    0.08
    诸
    0.08
    缦
    0.08
    åĽºå®ļçļĦ
    0.08
    管å±Ģ
    0.08
    Er
    0.08
    нак
    0.08
    Activations Density 0.205%

    No Known Activations