© 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. 40214
    Prev
    Next
    INDEX
    Explanations

    create new

    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
     hopefully
    -0.08
    æ¥
    -0.08
    hopefully
    -0.07
     prém
    -0.07
    ä¹ħ
    -0.06
    athan
    -0.06
    ç¶
    -0.06
    æķ
    -0.06
    eis
    -0.06
    elain
    -0.06
    POSITIVE LOGITS
    pone
    0.07
    åİĭåĬĽå¤§
    0.07
    åħ¨åĮħ
    0.07
    ãĤµãĥ¼ãĥĵãĤ¹ãĤĴ
    0.07
    cule
    0.07
    ines
    0.07
    åħ¨éĥ¨åĨħ容
    0.07
    ä¸Ģéĩij
    0.07
    æī©å®¹
    0.07
    ocache
    0.07
    Activations Density 0.006%

    No Known Activations