© 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. 19130
    Prev
    Next
    INDEX
    Explanations

    aerial warfare

    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
    ÙĦاÙĨ
    -0.09
    ç¬Ħ
    -0.09
     Ashton
    -0.09
    æ¿ij
    -0.08
    counts
    -0.08
    atus
    -0.08
    ool
    -0.08
    æ±ĩéĽĨ
    -0.08
    ature
    -0.08
    ia
    -0.08
    POSITIVE LOGITS
    ä¸ļ绩
    0.12
    羡
    0.10
    å´İ
    0.10
    çļĦ表çİ°
    0.10
    _disp
    0.10
    éªĦ
    0.10
    åĽŀæĬ¥
    0.09
    表çİ°
    0.09
    disp
    0.09
    vsp
    0.09
    Activations Density 0.023%

    No Known Activations