© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11043
    Prev
    Next
    INDEX
    Explanations

    vat, curl, copy, lava, sorted, label, attack, window, log, namespace

    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
    ISTA
    -0.07
    FSIZE
    -0.07
    änder
    -0.06
    ä¸Ńåħ±
    -0.06
    taa
    -0.06
    ä¸įäºī
    -0.06
    éĽ¾
    -0.06
    @hotmail
    -0.06
    iac
    -0.06
    Convertible
    -0.06
    POSITIVE LOGITS
    izr
    0.08
    åħ¬åħ±é¢Ħç®Ĺ
    0.07
    ↵        ↵        ↵
    0.07
     weiber
    0.07
    تÙĥ
    0.07
     dejt
    0.07
    ikal
    0.07
    eneral
    0.07
    èĮī
    0.07
    irtual
    0.06
    Activations Density 0.266%

    No Known Activations