© 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. 64621
    Prev
    Next
    INDEX
    Explanations

    the following

    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
    ambo
    -0.09
    миÑĤ
    -0.08
    gba
    -0.08
    ;]/
    -0.08
     ës
    -0.08
    ÃģC
    -0.08
     opd
    -0.08
    isial
    -0.07
    ãĢij,ãĢIJ
    -0.07
    onc
    -0.07
    POSITIVE LOGITS
    el
    0.08
    erder
    0.07
    æ´Ĺ
    0.06
    iere
    0.06
    éĺ
    0.06
    ï¼Ī
    0.06
    à»ī
    0.06
    å°±
    0.06
    ichel
    0.06
    UGH
    0.06
    Activations Density 1.033%

    No Known Activations