© 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. 40739
    Prev
    Next
    INDEX
    Explanations

    ignoring or setting aside

    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
    oreach
    -0.07
    ALO
    -0.07
    edah
    -0.07
    veys
    -0.07
    esper
    -0.07
    мÑĥÑĤ
    -0.07
    èĢĮä¸įæĺ¯
    -0.07
    ngle
    -0.07
     MATERI
    -0.07
    ALLY
    -0.07
    POSITIVE LOGITS
     complexities
    0.10
    åħ¶ä»ĸçļĦ
    0.08
    ä»»ä½ķåħ¶ä»ĸ
    0.08
    åį¿
    0.07
    éĻ¶éĨī
    0.07
    å¤įæĿĤæĢ§
    0.07
     complic
    0.07
    abilities
    0.07
     except
    0.07
     other
    0.07
    Activations Density 0.014%

    No Known Activations