© 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. 12818
    Prev
    Next
    INDEX
    Explanations

    and or contrasting options

    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
    æľīæĺİæĺ¾çļĦ
    -0.08
    åĬłæĭ¿å¤§
    -0.07
    aser
    -0.07
    &apos
    -0.07
     professionalism
    -0.07
    aurus
    -0.06
    zilla
    -0.06
    alc
    -0.06
    edom
    -0.06
     specifics
    -0.06
    POSITIVE LOGITS
    erson
    0.09
    款车åŀĭ
    0.08
    inded
    0.08
    /or
    0.08
    rogen
    0.07
    renom
    0.07
    agged
    0.07
    oled
    0.07
    ERTA
    0.07
    å±ħæĺĵ
    0.07
    Activations Density 0.381%

    No Known Activations