© 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. 26856
    Prev
    Next
    INDEX
    Explanations

    focus / want / narrow

    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
    åħ·æľī以ä¸ĭ
    -0.08
    Suit
    -0.07
     Suit
    -0.07
    è¿ĺåı¯èĥ½
    -0.07
     Suites
    -0.07
     suites
    -0.07
    inie
    -0.06
    acher
    -0.06
    ongs
    -0.06
    suit
    -0.06
    POSITIVE LOGITS
    kömm
    0.08
    ä¸įçĦ¶
    0.08
    àµ
    0.07
     /.
    0.07
     focused
    0.07
    ciel
    0.07
    indre
    0.07
    fera
    0.07
    าà¸ģล
    0.07
     âĤ¬.
    0.07
    Activations Density 0.002%

    No Known Activations