© 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. 26540
    Prev
    Next
    INDEX
    Explanations

    string manipulation code

    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
    tib
    -0.07
    дем
    -0.07
    让家éķ¿
    -0.07
    è¿ĽéĢĢ
    -0.07
    cob
    -0.06
    çĻ¾å®¶
    -0.06
    hy
    -0.06
    +l
    -0.06
    hd
    -0.06
    bh
    -0.06
    POSITIVE LOGITS
    -wide
    0.08
    åĭĴæĸ¯
    0.07
    appable
    0.07
    .removeChild
    0.07
    æľīè°ģ
    0.07
    jal
    0.07
     divis
    0.07
    elize
    0.07
    ahre
    0.07
    ears
    0.07
    Activations Density 0.004%

    No Known Activations