© 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. 33757
    Prev
    Next
    INDEX
    Explanations

    output file sequence

    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
    uali
    -0.06
    à¹Ħà¸ģล
    -0.06
    çĦ¶åIJİæĬĬ
    -0.06
    åį±
    -0.06
    åı£
    -0.06
    igm
    -0.06
    Einst
    -0.06
    è´Ŀåħĭ
    -0.06
    è¡£
    -0.06
    igate
    -0.06
    POSITIVE LOGITS
     ([[
    0.08
    amel
    0.08
     (::
    0.08
    -bot
    0.08
    çŁ
    0.08
    çľ·
    0.08
    çĨ¬
    0.07
    Ñıви
    0.07
    æĬļ
    0.07
    ien
    0.07
    Activations Density 0.001%

    No Known Activations