© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61632
    Prev
    Next
    INDEX
    Explanations

    "The" followed by project names

    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
    èµ·è§ģ
    -0.08
    witz
    -0.08
    side
    -0.07
    set
    -0.07
    rave
    -0.07
    da
    -0.07
    ment
    -0.07
    de
    -0.07
    ìĸ¸
    -0.07
    rieg
    -0.07
    POSITIVE LOGITS
    oretical
    0.15
    odor
    0.12
    oret
    0.10
    odore
    0.10
    ories
    0.10
    odoro
    0.09
    æĤ¨åı¯èĥ½
    0.09
    ãĤĵãģ³
    0.09
    istic
    0.09
    fts
    0.09
    Activations Density 0.850%

    No Known Activations