© 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. 49226
    Prev
    Next
    INDEX
    Explanations

    update or info

    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
    obo
    -0.06
    aknya
    -0.06
     }>
    -0.06
    '%(
    -0.06
    E
    -0.06
    ROUT
    -0.06
    A
    -0.06
    ']}
    -0.06
    ãĥ¶
    -0.05
    ortal
    -0.05
    POSITIVE LOGITS
    udre
    0.08
    ÙĩاÙĨ
    0.08
    elves
    0.08
    endr
    0.08
    oleon
    0.08
    euw
    0.08
    tml
    0.07
    blement
    0.07
    acam
    0.07
    heids
    0.07
    Activations Density 0.021%

    No Known Activations