© 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. 18630
    Prev
    Next
    INDEX
    Explanations

    asking questions about papers

    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
    ائÙħØ©
    -0.08
    enzi
    -0.07
    innacle
    -0.07
    æĶ¾çľ¼
    -0.07
     Postar
    -0.07
    aces
    -0.07
    comb
    -0.07
     Hayward
    -0.07
    Å¡nj
    -0.07
    imeline
    -0.07
    POSITIVE LOGITS
    çĪ±æĥľ
    0.08
    arith
    0.07
     embarrass
    0.07
     enunci
    0.07
    éĹ®é¢ĺçļĦèĥ½åĬĽ
    0.07
    渤
    0.06
    (LP
    0.06
     mathematical
    0.06
    å»ĸ
    0.06
     description
    0.06
    Activations Density 0.025%

    No Known Activations