© 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. 8431
    Prev
    Next
    INDEX
    Explanations

    function ( p | given | that | in )

    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
     stringBuilder
    -0.07
    arks
    -0.07
    gers
    -0.07
    джа
    -0.07
    è¹ĭ
    -0.07
     effettuata
    -0.06
    orti
    -0.06
    گاÙĩ
    -0.06
    aths
    -0.06
    reibung
    -0.06
    POSITIVE LOGITS
    nalité
    0.11
    er
    0.10
    ality
    0.10
    /method
    0.10
    naire
    0.10
    nalités
    0.10
    nal
    0.10
    ally
    0.10
    nel
    0.09
    ially
    0.09
    Activations Density 0.086%

    No Known Activations