© 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. 57160
    Prev
    Next
    INDEX
    Explanations

    code constructs (if, to, map, select)

    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
    çĻ»å½ķåIJİæŁ¥çľĭ
    -0.10
     admittedly
    -0.09
    reis
    -0.09
    ä¸į误
    -0.08
    ][_
    -0.08
    anderia
    -0.08
    æľīå¿ĥ人
    -0.08
    <|box_end|>
    -0.08
    /umd
    -0.08
    æī«æııäºĮç»´çłģä¸ĭè½½
    -0.08
    POSITIVE LOGITS
     âĨIJ
    0.07
    :
    0.06
     (
    0.06
    æĺ¾
    0.06
    å
    0.06
    0.06
    ť
    0.06
    èĭ¥å¹²
    0.06
     X
    0.06
    aining
    0.06
    Activations Density 0.020%

    No Known Activations