© 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. 26568
    Prev
    Next
    INDEX
    Explanations

    Sunderland or Vanderbilt

    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
    èĻ±
    -0.12
     sÆ°
    -0.10
    åij·
    -0.10
    æ¯ıèĤ¡
    -0.09
    ÑijÑĢ
    -0.09
    æѧ
    -0.09
    ory
    -0.09
    æ©Ľ
    -0.09
    èĻ«
    -0.09
    è§Ħ模以ä¸Ĭ
    -0.09
    POSITIVE LOGITS
    èĬ±å¼Ģ
    0.09
    edException
    0.09
     Commentary
    0.09
    ä¸įäºĨ
    0.09
    0.09
    hill
    0.08
    rine
    0.08
    æĺ§
    0.08
    _DIAG
    0.08
    ably
    0.08
    Activations Density 0.009%

    No Known Activations