© 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. 19313
    Prev
    Next
    INDEX
    Explanations

    dislocation, hernia, bowel, meningitis

    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
    dur
    -0.08
    elt
    -0.07
     targeting
    -0.07
    á»ĩt
    -0.07
    硬æľĹ
    -0.07
    ÙĦز
    -0.07
    è°ģçŁ¥
    -0.06
    èĦĬ
    -0.06
    rette
    -0.06
     ramp
    -0.06
    POSITIVE LOGITS
    æīŃ
    0.07
    繫
    0.07
    ç¸
    0.07
    à¸Ĭัà¹Īวà¸Ħราว
    0.07
    åĩºèµ°
    0.07
    egar
    0.07
    éĶĻä½į
    0.07
    åĵŃéĹ¹
    0.07
    ropa
    0.07
    导
    0.07
    Activations Density 0.092%

    No Known Activations