© 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. 7496
    Prev
    Next
    INDEX
    Explanations

    place names ending in boro, ville, bridge, berg

    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
    管å§Ķä¼ļ
    -0.08
    à¸Ħัà¸ļ
    -0.08
     opro
    -0.08
    éħĴå±ĭ
    -0.08
    _pas
    -0.08
    æ·Į
    -0.08
    Looper
    -0.07
     Goose
    -0.07
    ulich
    -0.07
    ataan
    -0.07
    POSITIVE LOGITS
    飶
    0.07
    achel
    0.07
     masked
    0.06
    ache
    0.06
    Then
    0.06
    acher
    0.06
    ief
    0.06
    ç¾İåѸ
    0.06
     Then
    0.06
    è¨Ģ
    0.06
    Activations Density 0.005%

    No Known Activations