© 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. 12153
    Prev
    Next
    INDEX
    Explanations

    trickle filters

    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
    agos
    -0.07
    ç¼¥
    -0.07
     suicide
    -0.07
     Suicide
    -0.07
    (pad
    -0.07
    èĭĹ
    -0.06
    ault
    -0.06
     mMap
    -0.06
     sä
    -0.06
    EMS
    -0.06
    POSITIVE LOGITS
     turbulent
    0.09
     shower
    0.08
     stagnant
    0.08
    è¿İé£İ
    0.08
    对æµģ
    0.08
    ulen
    0.07
    abeth
    0.07
     Reynolds
    0.07
    æİĴçĥŁ
    0.07
    .guid
    0.07
    Activations Density 0.002%

    No Known Activations