© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20737
    Prev
    Next
    INDEX
    Explanations

    numbers ending with 0, 1, 3, 5, 7, 9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /grpc
    -0.07
    éľ
    -0.07
    aign
    -0.07
    iau
    -0.06
    é
    -0.06
    æĻĴ
    -0.06
     jäm
    -0.06
    æĸ°è½¦
    -0.06
    åħ¨çĽĺ
    -0.06
    mail
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.08
    åĽ½å¼º
    0.08
    é»Ħç´ł
    0.07
    æŃĩå°Ķ
    0.07
    erson
    0.07
    çĶµè®¯
    0.07
     Mot
    0.07
     ÐļалÑĥ
    0.07
    ìħĢ
    0.07
    á»ħn
    0.07
    Activations Density 0.029%

    No Known Activations