© 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. 30682
    Prev
    Next
    INDEX
    Explanations

    private detective

    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
    agra
    -0.08
    ç¬Ļ
    -0.07
    anner
    -0.07
    æ±ĩ
    -0.06
    å¹ħ
    -0.06
    áte
    -0.06
     schl
    -0.06
    okol
    -0.06
    ruta
    -0.06
    ugat
    -0.06
    POSITIVE LOGITS
    lest
    0.09
    sworth
    0.08
    uri
    0.08
    chor
    0.08
    isa
    0.07
    cth
    0.07
    reur
    0.07
    iches
    0.07
    Ñİз
    0.07
    egan
    0.07
    Activations Density 0.398%

    No Known Activations