© 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. 63686
    Prev
    Next
    INDEX
    Explanations

    storage capacity

    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
    涯
    -0.07
    å®Ĺ
    -0.07
    éļħ
    -0.07
     retained
    -0.07
    éĻħ
    -0.07
    _attrib
    -0.07
    open
    -0.07
    åķ
    -0.07
    å¸Ń
    -0.07
     retains
    -0.06
    POSITIVE LOGITS
    æĹłæ³ķ满足
    0.10
    æĺ¯ä¸įåı¯èĥ½
    0.09
    çļĦéĻIJåĪ¶
    0.08
    emez
    0.08
    éĻIJåĪ¶äºĨ
    0.08
    éĥ½ä¸įåı¯èĥ½
    0.08
     unable
    0.08
    amay
    0.08
     impossible
    0.08
    rott
    0.08
    Activations Density 0.041%

    No Known Activations