© 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. 14725
    Prev
    Next
    INDEX
    Explanations

    okay, so

    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
    пиÑĤа
    -0.07
    jala
    -0.07
    çľº
    -0.07
    æĢľ
    -0.07
     tro
    -0.07
    Ross
    -0.07
    ixon
    -0.07
     Gregory
    -0.06
    åѤåįķ
    -0.06
    ¤
    -0.06
    POSITIVE LOGITS
    met
    0.07
    richten
    0.07
    ivic
    0.07
    åĶ¤
    0.07
    æĵĩ
    0.06
    è¾¾åħĭ
    0.06
    hun
    0.06
     indir
    0.06
    amad
    0.06
    UNK
    0.06
    Activations Density 0.001%

    No Known Activations