© 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. 10933
    Prev
    Next
    INDEX
    Explanations

    unfamiliar characters

    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
    è§Ĥä¼Ĺ
    -0.09
    å·Ŀ
    -0.09
    æĶ¸
    -0.09
    rray
    -0.09
    Listeners
    -0.09
    .pan
    -0.08
    дÑĥ
    -0.08
    æĽ²
    -0.08
     listeners
    -0.08
     Furious
    -0.08
    POSITIVE LOGITS
    éĻĮçĶŁ
    0.10
    强çĥĪçļĦ
    0.10
    çľ¼åīįçļĦ
    0.10
    çļĦæĥ³æ³ķ
    0.09
    çľĭä»ĸ
    0.09
     ÑģÑĤепени
    0.09
     unfamiliar
    0.09
    çļĦçĥŃæĥħ
    0.08
    .blob
    0.08
    ç«ŁçĦ¶
    0.08
    Activations Density 0.052%

    No Known Activations