© 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. 30703
    Prev
    Next
    INDEX
    Explanations

    second

    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
    orre
    -0.08
    次éĺħ读
    -0.08
    alion
    -0.07
    ache
    -0.07
    >>()
    -0.07
    æĻ©
    -0.07
    uille
    -0.07
    elj
    -0.07
    ilia
    -0.07
    /{{
    -0.07
    POSITIVE LOGITS
    zysz
    0.07
    odr
    0.07
    ãģĿãĤĮ
    0.06
    åı¦
    0.06
    æĮ
    0.06
     encodeURIComponent
    0.06
    ancio
    0.06
    亡
    0.06
    æªĢ
    0.06
    ettino
    0.06
    Activations Density 0.025%

    No Known Activations