© 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. 18301
    Prev
    Next
    INDEX
    Explanations

    complete or incomplete

    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
    ç½Ħ
    -0.09
    æħ£ãĤĮ
    -0.09
    æĪIJ为ä¸ŃåĽ½
    -0.09
    é£ı
    -0.08
    ableObject
    -0.08
    å¼Ģåıij建设
    -0.08
    çŃĭ
    -0.08
    çķı
    -0.08
    æĸ°éĹ»è®°èĢħ
    -0.08
    _TestCase
    -0.08
    POSITIVE LOGITS
    å®Įæķ´
    0.25
    å®Įæķ´çļĦ
    0.21
     completeness
    0.21
     incomplete
    0.20
    Incomplete
    0.20
    å®Įæķ´æĢ§
    0.20
    .complete
    0.16
    å®Įå¤ĩ
    0.16
    complete
    0.16
     Complete
    0.16
    Activations Density 0.125%

    No Known Activations