© 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. 907
    Prev
    Next
    INDEX
    Explanations

    subtype and encoding

    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
    çŃīåľ°çļĦ
    -0.08
    ices
    -0.08
    ice
    -0.08
     Kemen
    -0.08
    agar
    -0.07
    é·¹
    -0.07
    çŃīåľ°
    -0.07
    enor
    -0.07
    å®ŀçĶ¨æĸ°åŀĭ
    -0.07
    agit
    -0.07
    POSITIVE LOGITS
    subtype
    0.08
    å±ħå¤ļ
    0.08
    _subtype
    0.07
    æħĭ
    0.06
     subtype
    0.06
    /auto
    0.06
    çĨ
    0.06
    è¾ŀ
    0.06
    èĤĩ
    0.06
     باÙĦÙĦÙĩ
    0.06
    Activations Density 0.359%

    No Known Activations