© 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. 31197
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and associated words

    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
    istic
    -0.09
    sm
    -0.08
    lessness
    -0.08
    lessly
    -0.07
    бÑĥдÑĮÑĤе
    -0.07
    磶
    -0.07
    erness
    -0.07
    ning
    -0.07
    æľīåĩł
    -0.06
    avanaugh
    -0.06
    POSITIVE LOGITS
    {}]
    0.09
    деÑģÑıÑĤ
    0.09
    ষà§įà¦ł
    0.08
    chnik
    0.08
    ctions
    0.08
    estig
    0.08
    arts
    0.08
    brio
    0.08
    ethyst
    0.08
    durch
    0.08
    Activations Density 0.807%

    No Known Activations