© 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. 3682
    Prev
    Next
    INDEX
    Explanations

    future tense auxiliary verbs

    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
    ocu
    -0.08
    untime
    -0.07
    çIJIJç¢İ
    -0.07
    VALUES
    -0.07
    åĦ¿
    -0.06
    oci
    -0.06
    witz
    -0.06
    iv
    -0.06
     Karn
    -0.06
    ates
    -0.06
    POSITIVE LOGITS
    idor
    0.08
    afir
    0.07
    å°±å½ĵ
    0.07
    _busy
    0.07
    çĴĢ
    0.07
    åĬłåĢį
    0.07
    haj
    0.06
    顺åħ¶èĩªçĦ¶
    0.06
    ä¸įäºī
    0.06
     duro
    0.06
    Activations Density 0.005%

    No Known Activations