© 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. 18372
    Prev
    Next
    INDEX
    Explanations

    military systems capability

    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
    _PHP
    -0.10
    inspace
    -0.09
     ÑģÑĤÑĥд
    -0.09
    AxisSize
    -0.09
    IVAL
    -0.09
    unist
    -0.09
    认
    -0.09
     kiss
    -0.09
    é»İæĺİ
    -0.09
    POSE
    -0.08
    POSITIVE LOGITS
    éĢŁåº¦å¿«
    0.10
    åħ±å»º
    0.10
    è§Ĩ
    0.09
    æĮĩæݧ
    0.09
    ä¸Ńæ¯Ĵ
    0.09
    æĭ´
    0.09
    å°±æĪIJäºĨ
    0.09
    åķĸ
    0.08
    å¤ļå°ijéĴ±
    0.08
    åı£å¾Ħ
    0.08
    Activations Density 0.142%

    No Known Activations