© 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. 16913
    Prev
    Next
    INDEX
    Explanations

    opeq_derived

    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
    çĿ¦
    -0.07
    her
    -0.06
    olum
    -0.06
    '
    -0.06
    volv
    -0.06
    кÑĢовен
    -0.06
    aver
    -0.06
    <
    -0.06
    æĶ¿
    -0.06
    æĬĬäºĭæĥħ
    -0.06
    POSITIVE LOGITS
    ktop
    0.09
    éĺħè¯»æľ¬æĸĩåīį
    0.08
    欣欣
    0.08
    zugehen
    0.08
    éĥ½å¤Ħäºİ
    0.08
    ImagePath
    0.08
    ORIZED
    0.08
    abo
    0.07
    OnInit
    0.07
    eben
    0.07
    Activations Density 0.329%

    No Known Activations