© 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. 40149
    Prev
    Next
    INDEX
    Explanations

    that was, that would

    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
     insomma
    -0.07
     therefore
    -0.07
    åĽłæѤ
    -0.07
    æĥ«
    -0.07
    åĽłæŃ¤åľ¨
    -0.07
     hence
    -0.06
    qe
    -0.06
    oc
    -0.06
    æīĢéĢłæĪIJçļĦ
    -0.06
    å®ŀå®ŀåľ¨åľ¨çļĦ
    -0.06
    POSITIVE LOGITS
    elpers
    0.08
    æĪij家çļĦ
    0.08
    åĭĩèĢħ
    0.07
    antry
    0.07
    ancio
    0.07
    à¹īà¸ĩ
    0.07
    Ñĭй
    0.07
    æĶ¯
    0.07
    åıĪåĥı
    0.07
    å°ıç¼ĸ
    0.07
    Activations Density 0.022%

    No Known Activations