© 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. 22044
    Prev
    Next
    INDEX
    Explanations

    requesting/inquiring

    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
    çķ¥æľī
    -0.07
    åĬ«
    -0.06
    ahn
    -0.06
    _pars
    -0.06
    iphers
    -0.06
    大ä¸ĸçķĮ
    -0.06
    ÑĢоди
    -0.06
    ahal
    -0.06
    ype
    -0.06
     Mak
    -0.06
    POSITIVE LOGITS
    请æĮī
    0.10
    è¦ģæ±Ĥåľ¨
    0.10
    è¦ģæĮīçħ§
    0.10
    æĮīè¦ģæ±Ĥ
    0.09
    è¦ģæ±Ĥèĩªå·±
    0.09
    rz
    0.09
    å·¥ä½ľè¦ģæ±Ĥ
    0.09
     requested
    0.09
    åħ·ä½ĵè¦ģæ±Ĥ
    0.08
    并æĮīçħ§
    0.08
    Activations Density 0.018%

    No Known Activations