© 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. 42719
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax

    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
     Gente
    -0.07
    æĪĸéĥ¨åĪĨ
    -0.07
    overs
    -0.07
    —"
    -0.06
    aroo
    -0.06
    éŨå¤ĸ
    -0.06
    -db
    -0.06
    ()'
    -0.06
    çĪ±çļĦ人
    -0.06
    gente
    -0.06
    POSITIVE LOGITS
    æīĢ
    0.07
    èij«
    0.07
    lich
    0.07
    çĶŁæ°´
    0.06
    ä¼´
    0.06
     Lump
    0.06
    <|box_end|>
    0.06
    éĤ£åı¯
    0.06
     recru
    0.06
    еÑĩ
    0.06
    Activations Density 0.151%

    No Known Activations