© 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. 37531
    Prev
    Next
    INDEX
    Explanations

    subway station

    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
    ately
    -0.10
    éĻIJãĤĬ
    -0.09
    ç¿ħèĨĢ
    -0.09
    没æľīæĥ³åĪ°
    -0.09
    ality
    -0.09
    lessly
    -0.09
    uffman
    -0.08
    oeff
    -0.08
    оÑģ
    -0.08
    ève
    -0.08
    POSITIVE LOGITS
    éĢŁåº¦å¿«
    0.09
    ä¸įéĢļ
    0.09
    è¯Ŀ说
    0.09
    lify
    0.09
    entifier
    0.09
    ä¸įå¼Ģ
    0.08
    ÑĢин
    0.08
    ereum
    0.08
    å·¥ä½ľèĢħ
    0.08
    ldr
    0.08
    Activations Density 0.002%

    No Known Activations