© 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. 12989
    Prev
    Next
    INDEX
    Explanations

    huh?

    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
    <|box_end|>
    -0.09
    esses
    -0.09
    æĢ§åľ°
    -0.08
    ãĨ
    -0.08
    âĸłâĸł
    -0.08
    ssc
    -0.08
    æīĭæľºç«Ļ
    -0.08
    yota
    -0.08
    uder
    -0.08
    itys
    -0.08
    POSITIVE LOGITS
    !
    0.08
    çĦ¶å¤§
    0.07
    .
    0.07
    åĪ©äºļ
    0.07
    ,
    0.06
    --
    0.06
    (--
    0.06
    ï¼Į
    0.06
    ~
    0.06
    .au
    0.06
    Activations Density 0.017%

    No Known Activations