© 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. 65074
    Prev
    Next
    INDEX
    Explanations

    names followed by punctuation or verbs

    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
    Ïģγ
    -0.08
    trut
    -0.07
    loquent
    -0.07
    -loving
    -0.07
    KHR
    -0.07
    éĶĢåĶ®çĥŃ线
    -0.07
    عÙĩد
    -0.07
    çijŀå®ī
    -0.07
    éĻIJè¡Į
    -0.07
    زش
    -0.07
    POSITIVE LOGITS
    çŃī人
    0.08
    çŃī人çļĦ
    0.08
    ä¹ħçļĦ
    0.07
     اÙĦباÙĦغ
    0.07
    夫å¦ĩ
    0.07
    eker
    0.07
    ãĤĪãģĨãģ«
    0.07
    elijke
    0.07
     confined
    0.07
    çĦ¶çļĦ
    0.07
    Activations Density 0.026%

    No Known Activations