© 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. 1548
    Prev
    Next
    INDEX
    Explanations

    punctuation and titles

    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
    's
    -0.07
     "
    -0.07
    -0.07
    ington
    -0.07
    ,
    -0.06
     inv
    -0.06
    flow
    -0.06
     âĢŀ
    -0.06
    .
    -0.06
     (
    -0.06
    POSITIVE LOGITS
    ebet
    0.09
    izin
    0.08
    esub
    0.08
    éĢģåĪ°äºĨ
    0.08
    æĹłéĹ»
    0.08
    ãĤ·ãĥ¼
    0.08
    éĢģèµ°
    0.08
    recken
    0.08
     pél
    0.08
    ÑĤеÑĢе
    0.08
    Activations Density 0.053%

    No Known Activations