© 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. 25358
    Prev
    Next
    INDEX
    Explanations

    previous, earlier, prior, subsequent

    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
    ç¬ĭ
    -0.08
    écu
    -0.08
    lags
    -0.08
    oÅĤ
    -0.08
    alts
    -0.07
    以ä¸ĭåĩł
    -0.07
    以ä¸ĭ为
    -0.07
    _LS
    -0.07
    iefs
    -0.07
    _Pos
    -0.07
    POSITIVE LOGITS
     previous
    0.10
    previous
    0.08
     earlier
    0.08
    æľīä½Ļ
    0.08
    å·²ç»ıå°Ĩ
    0.08
    .previous
    0.07
    aylor
    0.07
     пÑĢедÑĭ
    0.07
    ãĤģãģ§
    0.07
    å·²ç»ıå®ĮæĪIJ
    0.07
    Activations Density 0.012%

    No Known Activations