© 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. 47942
    Prev
    Next
    INDEX
    Explanations

    as [NOUN]

    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
    社ä¼ļåĬĽéĩı
    -0.09
    åľ°äºļ
    -0.08
     przyj
    -0.08
    çļĦè¿ĺæľī
    -0.08
    spo
    -0.08
    çļĦåħ·ä½ĵæĥħåĨµ
    -0.07
    ali
    -0.07
    ãĤ·ãĥ§ãĥĥãĥĪ
    -0.07
    setError
    -0.07
    éĹ®é¢ĺæĺ¯
    -0.07
    POSITIVE LOGITS
    ä½ľä¸º
    0.08
    ä½ľçĤº
    0.08
    çĸij
    0.07
     sebagai
    0.06
    ãĤıãģĸ
    0.06
    xaa
    0.06
    为主è¦ģ
    0.06
     ÑģвоеобÑĢаз
    0.06
    agina
    0.06
    à¹Ģà¸Ľà¹ĩà¸Ļà¸ķัว
    0.06
    Activations Density 0.477%

    No Known Activations