© 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. 62217
    Prev
    Next
    INDEX
    Explanations

    military academies and graduations

    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
    ä¸įæĺĵ
    -0.09
    å·§
    -0.09
    妥
    -0.09
    _FL
    -0.09
    è§ĨåIJ¬
    -0.09
    onium
    -0.08
    æī¬
    -0.08
    æ³ł
    -0.08
    vox
    -0.08
     Corner
    -0.08
    POSITIVE LOGITS
    éĻĨåĨĽ
    0.15
    åĨĽå®ĺ
    0.15
    å°ĨåĨĽ
    0.14
    士åħµ
    0.13
    åıĤè°ĭ
    0.12
    åĨĽäºĭ
    0.11
     military
    0.11
     soldiers
    0.11
    èĢģåħµ
    0.11
    é»ĦåŁĶ
    0.11
    Activations Density 0.122%

    No Known Activations