© 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. 48884
    Prev
    Next
    INDEX
    Explanations

    connectivity and disconnection

    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
    velt
    -0.07
    _Base
    -0.07
     Deal
    -0.07
    ondi
    -0.07
    åı¯è¯»
    -0.06
    veld
    -0.06
     tac
    -0.06
     aggress
    -0.06
    赤水
    -0.06
     Sos
    -0.06
    POSITIVE LOGITS
     connectivity
    0.10
    /connect
    0.09
    connect
    0.08
     Connectivity
    0.08
    è¿ŀéĢļ
    0.08
    Disconnect
    0.08
     resilient
    0.08
    èĦĨå¼±
    0.08
    è¿ŀæİ¥
    0.07
    ween
    0.07
    Activations Density 0.004%

    No Known Activations