© 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. 55449
    Prev
    Next
    INDEX
    Explanations

    patched, this, the, o.o, the, started, ., both, added, we

    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
    -0.07
    /
    -0.07
    ory
    -0.06
    _
    -0.06
    in
    -0.06
    ilda
    -0.06
    �
    -0.06
    us
    -0.06
     [âĢ¦]
    -0.06
    è¿Ļå°±
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.10
    croft
    0.10
    grama
    0.09
     ç§ģ
    0.09
    colas
    0.09
    raphe
    0.09
    人已
    0.09
    stuhl
    0.09
    é¢Ħç¥Ŀ
    0.09
    å°¤
    0.08
    Activations Density 0.001%

    No Known Activations