© 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. 48111
    Prev
    Next
    INDEX
    Explanations

    is / are followed by descriptive words

    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
    éĢĤå½ĵåľ°
    -0.07
    åħ¨éĿ¢åıijå±ķçļĦ
    -0.07
    åŃ½
    -0.07
    建æľī
    -0.07
     Secur
    -0.07
    áºŃn
    -0.07
    羣æľī
    -0.07
    apul
    -0.07
     possessed
    -0.07
    çĶĦ
    -0.07
    POSITIVE LOGITS
    obb
    0.07
    елей
    0.07
     probably
    0.06
    udara
    0.06
    иви
    0.06
    oggle
    0.06
    ¶
    0.06
    tej
    0.06
     thugs
    0.06
    mise
    0.06
    Activations Density 0.038%

    No Known Activations