© 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. 18056
    Prev
    Next
    INDEX
    Explanations

    simple, easy, straightforward

    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
    ä¸įèĥ½åIJĥ
    -0.08
    ä¸ĢçĤ¹ä¸Ģæ»´
    -0.08
    å°±ä¸įèĥ½
    -0.07
    ä¸įæĹ©
    -0.07
    ä¸įçĶĺå¿ĥ
    -0.07
    lott
    -0.07
    NotAllowed
    -0.07
    ä¸įéĢı
    -0.07
     Cannot
    -0.07
    _busy
    -0.07
    POSITIVE LOGITS
     easier
    0.21
     easy
    0.17
    æ¯Ķè¾ĥ容æĺĵ
    0.17
    easy
    0.17
     simpler
    0.17
     easiest
    0.16
     straightforward
    0.16
    åıªéľĢ
    0.16
     ease
    0.16
    æĽ´å®¹æĺĵ
    0.16
    Activations Density 0.269%

    No Known Activations