© 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. 7318
    Prev
    Next
    INDEX
    Explanations

    strong evidence

    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
    ahaya
    -0.10
    ASTER
    -0.09
    raries
    -0.09
     ulang
    -0.09
    å¿ĺè¿Ķ
    -0.09
    uskan
    -0.09
    ÅĽwiad
    -0.09
    æŃ¤èµ·
    -0.09
    wege
    -0.09
    aras
    -0.09
    POSITIVE LOGITS
     mẽ
    0.13
    à¹Ĩ
    0.10
    ened
    0.09
    æľīåĬĽçļĦ
    0.09
    ness
    0.09
    issimo
    0.08
    holds
    0.08
    evity
    0.08
    æľīåĬĽ
    0.08
    stown
    0.08
    Activations Density 0.036%

    No Known Activations