© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50491
    Prev
    Next
    INDEX
    Explanations

    other parts or remaining portions

    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
    éĺ¶æ®µæĢ§
    -0.09
    éĺ´å½±
    -0.08
    轩
    -0.08
     Highlander
    -0.08
    shadow
    -0.08
    ç¼ĺ
    -0.08
    acus
    -0.08
    stage
    -0.08
    ppy
    -0.08
     Mata
    -0.08
    POSITIVE LOGITS
    ä»ħä¾Ľ
    0.09
    åħħå½ĵ
    0.09
    æīĭæĮģ
    0.09
    krit
    0.09
    é¬ĥ
    0.09
    å¿ĥä¸Ń
    0.09
    åī©ä¸ĭ
    0.08
    ÐĿÐIJ
    0.08
    åĤ§
    0.08
    éĹ½
    0.08
    Activations Density 0.005%

    No Known Activations