© 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. 56103
    Prev
    Next
    INDEX
    Explanations

    tuning methods

    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
    _SANITIZE
    -0.08
    kost
    -0.08
    }catch
    -0.07
    ukul
    -0.07
    boh
    -0.07
    åı¯æĥ³
    -0.07
    umbu
    -0.06
    oles
    -0.06
    EEK
    -0.06
    çº
    -0.06
    POSITIVE LOGITS
    neb
    0.07
    ä¹į
    0.07
    elos
    0.07
    urie
    0.07
    æ´»åĬ¨æĸ¹æ¡Ī
    0.07
     coba
    0.07
     [,
    0.07
    ä»ĺãģij
    0.06
    &S
    0.06
    çŃĶæ¡Ī解æŀIJ
    0.06
    Activations Density 0.013%

    No Known Activations