© 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. 39268
    Prev
    Next
    INDEX
    Explanations

    performance. compatibility. stability. feel. usefulness. range. activities

    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
    ạng
    -0.08
    :convert
    -0.08
    UILTIN
    -0.07
    ories
    -0.07
    _kw
    -0.07
    åħ´æĹº
    -0.07
    ulum
    -0.07
    icola
    -0.07
    çİĩé«ĺ
    -0.07
    аÑģÑĭ
    -0.07
    POSITIVE LOGITS
    ä¿ĿçķĻäºĨ
    0.09
    ä¿ĿçķĻ
    0.09
     sacrificed
    0.09
     preserving
    0.09
    åħ¼é¡¾
    0.08
    åİŁæľī
    0.08
    çīºçī²
    0.08
     unaffected
    0.08
     preserve
    0.08
    以åħįå½±åĵį
    0.08
    Activations Density 0.257%

    No Known Activations