© 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. 56173
    Prev
    Next
    INDEX
    Explanations

    national security

    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
    _packets
    -0.08
    acey
    -0.08
    ç¯Ļ
    -0.08
    æ¡IJ
    -0.08
    åģļå¾Ĺ
    -0.08
    æij¸
    -0.08
    HEN
    -0.08
    对æłĩ
    -0.08
    _PACKET
    -0.08
    ected
    -0.08
    POSITIVE LOGITS
    /person
    0.09
    riz
    0.09
    bur
    0.09
    踪
    0.09
    欢è¿İ
    0.08
    置身
    0.08
    åıĹä¸įäºĨ
    0.08
    æģ¸
    0.08
    åĺĺ
    0.08
    á»ĩu
    0.08
    Activations Density 0.020%

    No Known Activations