© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8806
    Prev
    Next
    INDEX
    Explanations

    end of sentence or punctuation

    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
    èĴĤæĸ¯
    -0.08
    apter
    -0.08
    rone
    -0.07
    示èĮĥæĢ§
    -0.07
    æ¶īåıĬçļĦ
    -0.07
    éĩij森
    -0.07
    xAA
    -0.07
    å·¥ç¨ĭéĻ¢éĻ¢å£«
    -0.07
    mys
    -0.06
    èĻĶ
    -0.06
    POSITIVE LOGITS
    æĮīçħ§è§Ħå®ļ
    0.10
    æĮīè§Ħå®ļ
    0.09
     according
    0.09
    æĮīçħ§
    0.09
    æį®è¯´
    0.08
    interpreted
    0.08
    according
    0.08
    约å®ļçļĦ
    0.08
    æĮīçħ§åĽ½å®¶
    0.07
     somew
    0.07
    Activations Density 0.204%

    No Known Activations