© 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. 42406
    Prev
    Next
    INDEX
    Explanations

    code delimiters and directives

    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
    avis
    -0.07
    worthy
    -0.07
    ÂŃ
    -0.06
    æĬķèµĦ管çIJĨ
    -0.06
    游åĽŃ
    -0.06
    æľĢ大ç¨ĭ度
    -0.06
    ict
    -0.06
    æķĻåŃ¦æ°´å¹³
    -0.06
    '
    -0.06
    âĢ
    -0.06
    POSITIVE LOGITS
    menes
    0.08
    éĺľ
    0.08
    sWith
    0.08
    .*(
    0.08
    ãĥ¼ãĤ¯
    0.08
    াà¦ķা
    0.08
    大åħ¬
    0.07
     ÄIJÃłm
    0.07
    -With
    0.07
    çĪ½
    0.07
    Activations Density 0.094%

    No Known Activations