© 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. 15796
    Prev
    Next
    INDEX
    Explanations

    purpose or mention

    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
    джа
    -0.08
    andest
    -0.07
     Anspruch
    -0.07
     veuillez
    -0.07
    eza
    -0.07
    å°Ķé¡¿
    -0.07
    деÑĢж
    -0.07
    请ç¨į
    -0.06
    éŃĦ
    -0.06
    ä¸ĭéĻįäºĨ
    -0.06
    POSITIVE LOGITS
    éĻ¤æѤä¹ĭå¤ĸ
    0.11
    éĻ¤äºĨ
    0.10
     except
    0.10
    except
    0.10
    éĻ¤æѤ
    0.09
    缴æݥ影åĵį
    0.09
    åıªæľīåľ¨
    0.09
    åıªæľīéĢļè¿ĩ
    0.09
     apart
    0.09
    éĻ¤äºĨåľ¨
    0.09
    Activations Density 0.076%

    No Known Activations