© 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. 18582
    Prev
    Next
    INDEX
    Explanations

    the ... most, one, right, area, sky, corner

    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
    ANEL
    -0.09
    olio
    -0.08
    ä¸Ńå¤ĸ
    -0.08
    apest
    -0.08
    å®Į好
    -0.08
    çĿ¦
    -0.08
    бл
    -0.08
    à¹ģà¸Ķ
    -0.08
    æĥij
    -0.08
    åĩºåħ¥
    -0.08
    POSITIVE LOGITS
    åIJ¼
    0.09
    ahkan
    0.09
    å¼Ĥåľ°
    0.08
    ãģĿãģĨãģ§
    0.08
    å¿Ĩ
    0.08
    æ°Ķ
    0.08
     fora
    0.08
     ê·¸ëłĩì§Ģ
    0.08
    nist
    0.08
    .instant
    0.08
    Activations Density 0.023%

    No Known Activations