© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 55699
    Prev
    Next
    INDEX
    Explanations

    time differences

    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
    rakt
    -0.09
    Ŀ
    -0.08
    aney
    -0.08
    ppe
    -0.08
    áter
    -0.08
    WithValue
    -0.08
    REEN
    -0.08
    è¿ijä¹īè¯į
    -0.08
    åħ¨åı°
    -0.07
     attrac
    -0.07
    POSITIVE LOGITS
     simult
    0.07
     Cia
    0.07
    代表çĿĢ
    0.07
    views
    0.06
    à¸Ĺม
    0.06
     subj
    0.06
    vere
    0.06
    éĴŁè¡¨
    0.06
    lices
    0.06
    以èĩªå·±
    0.06
    Activations Density 0.001%

    No Known Activations