© 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. 57080
    Prev
    Next
    INDEX
    Explanations

    asking for help or instructions

    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
    hound
    -0.07
     Regents
    -0.07
    stdin
    -0.07
    并举
    -0.07
    å°ĺåŁĥ
    -0.07
     Suddenly
    -0.07
    inda
    -0.07
    æĬĢæľ¯è§ĦèĮĥ
    -0.06
    Apparently
    -0.06
    糸
    -0.06
    POSITIVE LOGITS
    æ£ĢæŁ¥
    0.08
     unconditional
    0.08
     explicitly
    0.07
    åıĬæŶ
    0.07
     check
    0.07
    alani
    0.07
    åĭĻ
    0.07
    enser
    0.07
    ritos
    0.07
    лав
    0.07
    Activations Density 0.278%

    No Known Activations