© 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. 34451
    Prev
    Next
    INDEX
    Explanations

    examples, as always, employing

    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
    plo
    -0.07
    ure
    -0.07
    tdown
    -0.07
    ä½ľåĵģä»ĭç»į
    -0.07
    erland
    -0.06
    çŃīåħ¶ä»ĸ
    -0.06
    tene
    -0.06
    è¡
    -0.06
     inferior
    -0.06
    IDAD
    -0.06
    POSITIVE LOGITS
    senz
    0.08
    aut
    0.07
     illustr
    0.07
    è¿ĻæľŁéĹ´
    0.07
     dabei
    0.07
     inters
    0.07
    ä¸įä¹ı
    0.06
    è¦ģ注éĩį
    0.06
    venuto
    0.06
    db
    0.06
    Activations Density 0.036%

    No Known Activations