© 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. 45381
    Prev
    Next
    INDEX
    Explanations

    applicant for legal aid

    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
    à¸Ĺัศà¸Ļà¹Į
    -0.08
    ored
    -0.07
    abbit
    -0.07
    undes
    -0.07
    ebin
    -0.07
    atings
    -0.07
    orgt
    -0.07
    /she
    -0.07
    ãĥ¼
    -0.07
    /her
    -0.07
    POSITIVE LOGITS
    eer
    0.09
    umerator
    0.08
    ered
    0.08
    ive
    0.08
    er
    0.08
    arat
    0.08
    GestureRecognizer
    0.08
    ees
    0.08
    aat
    0.08
    erst
    0.08
    Activations Density 0.030%

    No Known Activations