© 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. 37566
    Prev
    Next
    INDEX
    Explanations

    positive or negative states

    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
    ÐķÐĿ
    -0.08
    顽强
    -0.08
    odos
    -0.08
    AndGet
    -0.08
    _dense
    -0.08
     outcome
    -0.08
     ÑĢавно
    -0.08
    åľ¨æѤ
    -0.07
    kers
    -0.07
    æѤåĪ»
    -0.07
    POSITIVE LOGITS
    å¸ĮæľĽéĢļè¿ĩ
    0.11
    å¸ĮæľĽèĥ½å¤Ł
    0.10
    è¿ĺéľĢ
    0.10
    ä¸ĢèĦ¸
    0.10
    ä¸įå°½
    0.10
     intact
    0.10
    éĻĮ
    0.09
    è¾Ļ
    0.09
    好è¯Ħ
    0.09
    宣称
    0.09
    Activations Density 0.114%

    No Known Activations