© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7542
    Prev
    Next
    INDEX
    Explanations

    buy from us

    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
     Carter
    -0.09
    aret
    -0.09
    éĢĤå®ľ
    -0.08
    é¸
    -0.08
    ParameterValue
    -0.08
    åĮĸ身
    -0.08
    vac
    -0.08
    rets
    -0.08
    sov
    -0.08
    /dev
    -0.08
    POSITIVE LOGITS
    ä¸įåIJĥ
    0.09
    çijķ
    0.08
    çļĦå¢ŀéķ¿
    0.08
    æµĵ缩
    0.08
     stall
    0.08
    Platform
    0.08
    å¾Ĺä½ı
    0.08
    è®´
    0.08
    å¹³åı°ä¸Ĭ
    0.08
    çļĦåľ°
    0.08
    Activations Density 0.042%

    No Known Activations