© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33369
    Prev
    Next
    INDEX
    Explanations

    numeric literals followed by punctuation

    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
    ...',
    -0.09
    <|im_start|>
    -0.08
    żd
    -0.08
    ...",
    -0.08
    亦çĦ¶
    -0.08
    \Unit
    -0.07
    èĢĮéĻį
    -0.07
    ]->
    -0.07
    abah
    -0.07
    ">%
    -0.07
    POSITIVE LOGITS
    èĻ½çĦ¶æĺ¯
    0.07
    hammer
    0.07
     originally
    0.06
    æ²ŁéĢļåĴĮ
    0.06
    éĥ¨åĪĨåĨħ容
    0.06
    obl
    0.06
     circulated
    0.06
    bli
    0.06
    aken
    0.06
    vide
    0.06
    Activations Density 0.109%

    No Known Activations