© 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. 65026
    Prev
    Next
    INDEX
    Explanations

    negative theology, incarnation, relative, illusion, Gospel

    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
    ðŁĴ
    -0.07
    æĹ·
    -0.07
    _rnn
    -0.07
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
     laure
    -0.07
    éĹ®é¢ĺåĪĨæŀIJ
    -0.07
     impro
    -0.07
    Ø´ØŃ
    -0.07
    æĹłæķħ
    -0.07
     mojo
    -0.07
    POSITIVE LOGITS
    羣çIJĨ
    0.09
    满足ä¸įåIJĮ
    0.08
    第ä¸Ģç§į
    0.08
    çī
    0.07
    éĴĪ对ä¸įåIJĮ
    0.07
     truth
    0.07
    对çĹĩä¸ĭèį¯
    0.07
    为äºĨä¸į
    0.07
     limited
    0.07
    æķĻä½ĵ
    0.07
    Activations Density 0.005%

    No Known Activations