© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48812
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and numbers

    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
     }}}
    -0.08
    кок
    -0.08
    enius
    -0.08
    ymar
    -0.08
    ?key
    -0.08
    ";}
    -0.07
    踩çĿĢ
    -0.07
    ixe
    -0.07
    imme
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    POSITIVE LOGITS
    elen
    0.07
     co
    0.06
    -errors
    0.06
    士æŀĹ
    0.06
    æĭİåĮħ
    0.06
    Globals
    0.06
    ä½Ĩä»į
    0.06
    éĩįéĩį
    0.06
    oke
    0.06
    idd
    0.05
    Activations Density 0.003%

    No Known Activations