© 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. 4297
    Prev
    Next
    INDEX
    Explanations

    solve, let, what, collect

    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
     tam
    -0.08
    ↵
    -0.07
    t
    -0.07
    ...
    -0.06
     ÑĤам
    -0.06
     Tam
    -0.06
     T
    -0.06
    ÙĤÙĪÙĦ
    -0.06
     "
    -0.06
    Âł
    -0.06
    POSITIVE LOGITS
    åľ¨æł¡åĽŃ
    0.08
     |–
    0.08
    beck
    0.08
    åħ¨éĿ¢è´¯å½»
    0.08
    (PR
    0.08
    </think>
    0.08
    _LSB
    0.08
    वà¤Ĥ
    0.08
    fran
    0.08
    iscard
    0.08
    Activations Density 0.017%

    No Known Activations