© 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. 32645
    Prev
    Next
    INDEX
    Explanations

    filtering for "only"

    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
    .standard
    -0.06
    åı¯æĥľ
    -0.06
     Kot
    -0.06
    ä¹İ
    -0.06
    ä¸įè¦ģåĨį
    -0.06
     Took
    -0.06
    æµģä¼ł
    -0.06
    _regular
    -0.05
    veen
    -0.05
    isez
    -0.05
    POSITIVE LOGITS
    only
    0.18
     only
    0.18
    -only
    0.17
    Only
    0.17
    _only
    0.17
     Only
    0.16
    ä»ħæľīçļĦ
    0.16
    ä»ħæľī
    0.15
    ONLY
    0.15
    ë§Į
    0.15
    Activations Density 0.188%

    No Known Activations