© 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. 20161
    Prev
    Next
    INDEX
    Explanations

    -en, -ene, -one, -ol suffix

    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
    LES
    -0.07
    tons
    -0.06
    áĥ¦
    -0.06
    lesa
    -0.06
    tauf
    -0.06
    åħ¨ä½ĵæķĻå¸Ī
    -0.06
    wel
    -0.06
    ä¸įä¸Ģ
    -0.06
    íݼ
    -0.06
    ekl
    -0.06
    POSITIVE LOGITS
    imit
    0.08
    åIJ«éĩij
    0.08
    uary
    0.08
    illez
    0.07
    åĬłæĭī
    0.07
    à¥įह
    0.07
    éĵ¶å±±
    0.07
    statt
    0.07
     |–
    0.07
    diy
    0.07
    Activations Density 0.009%

    No Known Activations