© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17857
    Prev
    Next
    INDEX
    Explanations

    names with suffixes or hyphens

    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
    estion
    -0.08
     коÑĤоÑĢо
    -0.08
    enance
    -0.07
    ctp
    -0.07
    ford
    -0.07
    为己
    -0.07
    ÙĪÙĨØ©
    -0.07
    elden
    -0.07
     europ
    -0.07
    elos
    -0.07
    POSITIVE LOGITS
    ä¸Ģä½ĵçļĦ
    0.07
    èĥģ
    0.07
    aÅĤ
    0.07
    äºĽ
    0.06
    nix
    0.06
    gether
    0.06
    æľ¬åľºæ¯ĶèµĽ
    0.06
    åĵ©
    0.06
    iÄĻ
    0.06
    uzzi
    0.06
    Activations Density 0.323%

    No Known Activations