© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13890
    Prev
    Next
    INDEX
    Explanations

    full-time view

    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
    çĽ²
    -0.07
     اط
    -0.07
     dig
    -0.07
    ='_
    -0.07
    å½ĵçĦ¶äºĨ
    -0.07
     dispens
    -0.07
     Handy
    -0.06
     blind
    -0.06
    çĴŁ
    -0.06
     angen
    -0.06
    POSITIVE LOGITS
    EAU
    0.08
    ixa
    0.07
    ¡´
    0.07
    enzo
    0.07
    æĥ¨éģŃ
    0.07
    ykk
    0.07
    çķ¦
    0.07
    apo
    0.07
    éĽªå³°
    0.07
    lande
    0.07
    Activations Density 0.065%

    No Known Activations