© 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. 25378
    Prev
    Next
    INDEX
    Explanations

    eight, 0, 1, 3, 6, 8, 9

    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
     {}
    -0.06
    j
    -0.06
    -0.06
    æ°ıæĹı
    -0.06
    æ´»è·ĥ
    -0.06
     {}".
    -0.06
    n
    -0.05
    uck
    -0.05
    -
    -0.05
     active
    -0.05
    POSITIVE LOGITS
    енок
    0.09
    åı¯æ¢¦
    0.09
    onos
    0.09
    roje
    0.09
    akis
    0.09
    λή
    0.09
    nett
    0.08
    anke
    0.08
    _SPR
    0.08
    .cv
    0.08
    Activations Density 0.002%

    No Known Activations