© 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. 60359
    Prev
    Next
    INDEX
    Explanations

    handle with care

    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
    ally
    -0.11
    earch
    -0.08
    utos
    -0.08
    ieÅĦ
    -0.08
    icch
    -0.08
    ़
    -0.08
    ajib
    -0.08
    -0.08
    มà¸Ļ
    -0.08
    orrow
    -0.07
    POSITIVE LOGITS
    bars
    0.11
    å¾Ĺå½ĵ
    0.10
    able
    0.09
    çĿ¬
    0.09
    Ùĭ
    0.09
    à¹īวย
    0.08
    uther
    0.08
    èĩªå¦Ĥ
    0.08
    è¿ĩçļĦ
    0.08
    ties
    0.08
    Activations Density 0.077%

    No Known Activations