© 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. 9559
    Prev
    Next
    INDEX
    Explanations

    names of people, companies, or things, often followed by specific suffixes

    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
    imony
    -0.09
    æij¸
    -0.08
    æĻĸ
    -0.08
    opus
    -0.08
    人æµģ
    -0.08
    piring
    -0.08
    èĩ³ä»Ĭ
    -0.08
    vironment
    -0.08
    ä¸įåĬ¨
    -0.08
    velopment
    -0.08
    POSITIVE LOGITS
    ç¨
    0.10
    æ±²
    0.10
    äºĨä¸ĢäºĽ
    0.09
    -widgets
    0.08
    产æĿĥ
    0.08
    mie
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    è§Ħå®ļçļĦ
    0.08
    æĮĩå®ļ
    0.08
    åį±å®³
    0.08
    Activations Density 0.324%

    No Known Activations