© 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. 38621
    Prev
    Next
    INDEX
    Explanations

    Abracadabra

    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
    aliz
    -0.07
    gek
    -0.07
     {}:
    -0.06
    )?.
    -0.06
     nanti
    -0.06
    @qq
    -0.06
    å½Ĵç»ĵ
    -0.06
    ax
    -0.06
     {}.
    -0.06
    upra
    -0.06
    POSITIVE LOGITS
    éo
    0.07
    åĭ¤åĭ¤æģ³æģ³
    0.07
    æľįåĬ¡åħ¬åı¸
    0.07
    ãĥĨãĥ¼ãĤ·ãĥ§ãĥ³
    0.07
    ALSE
    0.07
    _UNS
    0.07
     equivalente
    0.07
    eof
    0.07
    俱ä¹IJéĥ¨
    0.07
    以ä¸Ĭå°±æĺ¯å°ıç¼ĸ
    0.07
    Activations Density 0.064%

    No Known Activations