© 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. 46250
    Prev
    Next
    INDEX
    Explanations

    reference points/basis/image/method

    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
    åįĹåĽ½
    -0.08
    æīĢæĢĿ
    -0.08
    onique
    -0.08
    oyo
    -0.08
    _queues
    -0.08
    ãĥģãĥĥãĤ¯
    -0.08
    _retry
    -0.08
    sembles
    -0.08
    onais
    -0.08
    naments
    -0.07
    POSITIVE LOGITS
    /reference
    0.11
    åŁºåĩĨ
    0.08
     reference
    0.08
    /target
    0.08
    anchor
    0.08
    лак
    0.08
    åıĤèĢĥ
    0.07
    åıĤçħ§
    0.07
    /base
    0.07
    (reference
    0.07
    Activations Density 0.136%

    No Known Activations