© 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. 62030
    Prev
    Next
    INDEX
    Explanations

    donkey, donation, don't, donator

    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
    ãģªãģĦ
    -0.11
    ÅĽci
    -0.09
    .cloudflare
    -0.09
     Vick
    -0.09
    ä¿®æŃ£
    -0.09
    ä¸Ģå¼Ģå§ĭå°±
    -0.09
     khấu
    -0.09
    å§Ķ书记
    -0.09
    æĬķä¿Ŀ
    -0.09
    说æĪij
    -0.09
    POSITIVE LOGITS
    nelly
    0.11
    åij½
    0.09
    å¥ĩå¦Ļ
    0.09
    æĹłæīĢè°ĵ
    0.09
    away
    0.09
    lap
    0.09
    er
    0.09
    ami
    0.08
    zen
    0.08
    sey
    0.08
    Activations Density 0.016%

    No Known Activations