© 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. 29563
    Prev
    Next
    INDEX
    Explanations

    radiographic contrast

    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
     Sinai
    -0.07
    neau
    -0.07
    æ´Ľå¤«
    -0.07
    å§ĭç»Ī以
    -0.07
    каÑĥ
    -0.07
    çĴ¨
    -0.07
    ä¸įæĹ©
    -0.07
     Breit
    -0.06
    raphe
    -0.06
    浸
    -0.06
    POSITIVE LOGITS
     worthy
    0.07
     aran
    0.07
    被æĬĵ
    0.07
    னà¯ģ
    0.07
    /tag
    0.07
    äºļçī¹
    0.07
    æĮŁ
    0.07
    BAN
    0.07
    ä¸Ģå®ļæľī
    0.06
    Executable
    0.06
    Activations Density 0.172%

    No Known Activations