© 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. 26581
    Prev
    Next
    INDEX
    Explanations

    code class/object names

    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
     latter
    -0.06
     except
    -0.06
    ä¿Ŀæľ¬
    -0.06
    ç¬
    -0.06
    Except
    -0.06
    except
    -0.06
    /grid
    -0.06
    andar
    -0.05
    -pdf
    -0.05
    åīįèĢħ
    -0.05
    POSITIVE LOGITS
    éĺħè¯»æľ¬æĸĩ
    0.09
    yé
    0.08
    .jet
    0.08
    usalem
    0.08
    éħĴå±ĭ
    0.08
    Äĥt
    0.08
    azon
    0.08
    åı¤å±ĭ
    0.08
    _UT
    0.07
     ÙħÙĨاط
    0.07
    Activations Density 0.016%

    No Known Activations