© 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. 56265
    Prev
    Next
    INDEX
    Explanations

    check reviews and read more

    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
    æĦīæĤ¦
    -0.09
    æĶ¾å¤§
    -0.09
    à¹Ĥà¸ķ
    -0.09
    åİŁåĪĽ
    -0.09
    resp
    -0.08
    æ¹ĸåĮº
    -0.08
    çĪ½
    -0.08
     Cornel
    -0.08
    .mb
    -0.08
    tl
    -0.08
    POSITIVE LOGITS
    ç½ijä¸Ĭ
    0.09
    认æ¸ħ
    0.09
    enda
    0.09
    itis
    0.09
    idos
    0.08
    ä»Ķç»Ĩ
    0.08
    kov
    0.08
    主æĿĥ
    0.08
     Gund
    0.08
    nants
    0.08
    Activations Density 0.035%

    No Known Activations