© 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. 58451
    Prev
    Next
    INDEX
    Explanations

    risk factors or assessment

    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
    entifier
    -0.08
    -Russian
    -0.08
    _stderr
    -0.08
    Ñĩини
    -0.08
     nhiên
    -0.08
    arity
    -0.08
    áĥ£áĥłáĥĺ
    -0.07
    sworth
    -0.07
     fleste
    -0.07
     grátis
    -0.07
    POSITIVE LOGITS
    ingly
    0.10
    fully
    0.09
    ened
    0.09
    lessly
    0.09
    iest
    0.09
    ful
    0.08
    à¸łà¸±à¸¢
    0.08
    éĢıäºĨ
    0.08
    andard
    0.08
    illing
    0.08
    Activations Density 0.045%

    No Known Activations