© 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. 39554
    Prev
    Next
    INDEX
    Explanations

    options, alternatives, or accomplishments

    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
    çŃīå¤ļç§į
    -0.07
     (?)
    -0.07
    erc
    -0.07
     sometimes
    -0.07
    (?)
    -0.07
    /cgi
    -0.07
     nowhere
    -0.07
    sometimes
    -0.06
    èµ·è§ģ
    -0.06
    æĬĢæľ¯è¦ģæ±Ĥ
    -0.06
    POSITIVE LOGITS
     ÙĪÙĥÙĬÙģ
    0.11
    以åıĬå¦Ĥä½ķ
    0.11
    åį³åľ¨
    0.09
    以åıĬåľ¨
    0.09
    åıĬåħ¶
    0.08
    æĢ§ä»¥åıĬ
    0.08
    :+
    0.08
     yakni
    0.08
    ivil
    0.08
     yaitu
    0.08
    Activations Density 0.036%

    No Known Activations