© 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. 13703
    Prev
    Next
    INDEX
    Explanations

    compute, using, paper, see, went, my

    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
    asted
    -0.08
    åĽłä¸ºåħ¶
    -0.08
    _met
    -0.07
    maak
    -0.07
     ðŁĺī
    -0.07
     heti
    -0.07
    ast
    -0.07
    é¦Ļæł¼éĩĮæĭī
    -0.07
    cese
    -0.07
    Injector
    -0.07
    POSITIVE LOGITS
    erven
    0.07
    çŃīå¤ļ项
    0.06
    åı¯çĶ³è¯·
    0.06
    以ä¸ĬåĨħ容
    0.06
    è¾Ľ
    0.06
    imismo
    0.06
    çĦ¶èĢĮåľ¨
    0.06
    ilik
    0.06
    dera
    0.06
     Fras
    0.06
    Activations Density 0.140%

    No Known Activations