© 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. 45225
    Prev
    Next
    INDEX
    Explanations

    And followed by a phrase

    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
    ä¸įçĦ¶
    -0.11
    otherwise
    -0.08
     otherwise
    -0.08
     deteri
    -0.08
    Otherwise
    -0.08
    åIJ¦åĪĻ
    -0.08
    entai
    -0.08
    åĭģ
    -0.08
    ersh
    -0.08
     Otherwise
    -0.07
    POSITIVE LOGITS
    h
    0.06
    Abb
    0.06
    ä¸īåįģåħŃ
    0.05
    T
    0.05
     krav
    0.05
    he
    0.05
    SAT
    0.05
    chado
    0.05
    æ´¾åıij
    0.05
    nus
    0.05
    Activations Density 0.081%

    No Known Activations