© 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. 19365
    Prev
    Next
    INDEX
    Explanations

    imagine you, Say the, As the, I use, The UL, Just save, I have, Her skin, Yes the

    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
    ivor
    -0.08
     respectivos
    -0.07
    óry
    -0.07
    ':''
    -0.07
     thereof
    -0.07
    itory
    -0.07
     respectivas
    -0.07
     اث
    -0.07
    amble
    -0.07
    éļıä¹ĭ
    -0.07
    POSITIVE LOGITS
    âij
    0.08
     firstly
    0.08
    oretical
    0.08
    !,
    0.07
    orem
    0.07
    fos
    0.07
    åħĪæĺ¯
    0.07
    oret
    0.07
    çĦ¶å¤§
    0.07
    é¦ĸåħĪ
    0.07
    Activations Density 0.071%

    No Known Activations