© 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. 24905
    Prev
    Next
    INDEX
    Explanations

    instructions or requirements

    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
    hopefully
    -0.08
    alise
    -0.08
    auses
    -0.08
    utant
    -0.07
    ensions
    -0.07
    Lim
    -0.07
     Zas
    -0.07
    å¦ĤåĽł
    -0.07
    auta
    -0.07
    eneral
    -0.07
    POSITIVE LOGITS
    èĩ³å°ij
    0.10
     mindestens
    0.09
    å¿ħé¡»æľī
    0.09
     ë°ĺëĵľìĭľ
    0.09
     préal
    0.09
    åħ·å¤ĩä¸Ģå®ļçļĦ
    0.09
    å¾Ĺæľī
    0.09
    è¦ģæľī
    0.08
     préalable
    0.08
    åħĪå°Ĩ
    0.08
    Activations Density 0.229%

    No Known Activations