© 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. 17921
    Prev
    Next
    INDEX
    Explanations

    way of defining

    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
    åIJĦé¡¹å·¥ä½ľ
    -0.10
    ä¸įå°ı
    -0.10
    车载
    -0.09
    æĺı
    -0.09
    微信åı·
    -0.09
    erde
    -0.09
    íķij
    -0.09
    äºĨä¸Ģ个
    -0.09
    ä¸Ģ个éĹ®é¢ĺ
    -0.09
    龸çİĭ
    -0.08
    POSITIVE LOGITS
    çľĭå¾ħ
    0.13
    åģļäºĭ
    0.10
    缸å¤Ħ
    0.10
    ToLower
    0.09
     наблÑİ
    0.09
    бÑĥÑĢ
    0.09
    åºĶ对
    0.09
    ган
    0.09
    IGIN
    0.08
    GetInstance
    0.08
    Activations Density 0.034%

    No Known Activations