© 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. 11307
    Prev
    Next
    INDEX
    Explanations

    continue reading

    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
    çĿĢ
    -0.07
     âĢ¦
    -0.07
    rich
    -0.07
    ergestellt
    -0.07
    ont
    -0.06
    #####
    -0.06
     &
    -0.06
     ...
    -0.06
    éĢ¢
    -0.06
    oure
    -0.06
    POSITIVE LOGITS
    .dsl
    0.08
    çIJ¦
    0.08
    KO
    0.07
     dayan
    0.07
    AttributeName
    0.07
    kert
    0.07
    æĸ°å¤©åľ°
    0.07
    èĩªè¾¾
    0.07
    olit
    0.07
    uncan
    0.07
    Activations Density 0.004%

    No Known Activations