© 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. 62578
    Prev
    Next
    INDEX
    Explanations

    hostile, adversary, confrontation, contentious

    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
    .spin
    -0.09
     fle
    -0.08
    PLE
    -0.08
    à¸Ńà¸ģ
    -0.08
    URY
    -0.07
     fork
    -0.07
    ILE
    -0.07
    ãģĤãģ£ãģ¦
    -0.07
    guns
    -0.07
    UTE
    -0.07
    POSITIVE LOGITS
    æ°Ķæ°Ľ
    0.11
    è¡ħ
    0.10
    æ°ĽåĽ´
    0.10
    çݯå¢ĥä¸ĭ
    0.09
     дÑĥÑħ
    0.09
    ä½ķåĨµ
    0.09
    åĬ¿å¤´
    0.09
    缮åħī
    0.09
    zyst
    0.09
    entine
    0.09
    Activations Density 0.034%

    No Known Activations