© 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. 30729
    Prev
    Next
    INDEX
    Explanations

    data entry and lists

    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
    _rsp
    -0.10
    esian
    -0.10
    apan
    -0.09
    esan
    -0.09
    广åijĬæľįåĬ¡
    -0.08
    IRON
    -0.08
    ImageContext
    -0.08
    æĸ¡
    -0.08
    _ARM
    -0.08
    Consumer
    -0.08
    POSITIVE LOGITS
    å½ķåħ¥
    0.16
    èĪ¶
    0.09
     Loader
    0.09
    æķ°æį®
    0.09
    fills
    0.09
    èıŁ
    0.09
    æķ¸æĵļ
    0.09
    gend
    0.09
     data
    0.09
    èĸħ
    0.09
    Activations Density 0.084%

    No Known Activations