© 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. 41565
    Prev
    Next
    INDEX
    Explanations

    described positive reviews

    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
    å½ĵçĦ¶
    -0.07
    opup
    -0.07
     (=
    -0.07
    iras
    -0.07
     конеÑĩно
    -0.06
     obviously
    -0.06
    cato
    -0.06
    thur
    -0.06
    离
    -0.06
     ;-)
    -0.06
    POSITIVE LOGITS
    acte
    0.08
    æī¹è©ķ
    0.07
    afil
    0.07
    åľı
    0.07
    è¿Ľè¡Įå®¡æł¸
    0.07
    ahi
    0.07
    以赴
    0.07
    Else
    0.07
    ç»ı审çIJĨ
    0.07
    审éĺħ
    0.07
    Activations Density 1.313%

    No Known Activations