© 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. 20728
    Prev
    Next
    INDEX
    Explanations

    git diff header indicators

    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
     ÑģлÑĥÑĩ
    -0.07
    ihn
    -0.07
    igue
    -0.07
    åı£çļĦ
    -0.07
     Peters
    -0.07
    gw
    -0.07
    饮
    -0.07
    ivery
    -0.07
    éĩ
    -0.06
    渡è¿ĩ
    -0.06
    POSITIVE LOGITS
    æĸ°æŧ
    0.10
    æŧ
    0.10
    Changes
    0.09
     changes
    0.09
    changes
    0.09
     CHANGE
    0.08
    æĸ°å¢ŀäºĨ
    0.08
     Changes
    0.08
    åİŁæľī
    0.08
     old
    0.08
    Activations Density 0.100%

    No Known Activations