© 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. 61851
    Prev
    Next
    INDEX
    Explanations

    actions after 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
    áng
    -0.07
    byname
    -0.06
    (AT
    -0.06
    ä¿ĬæĿ°
    -0.06
    ueb
    -0.06
    LK
    -0.06
    (KP
    -0.06
    麽
    -0.06
    chy
    -0.05
    KER
    -0.05
    POSITIVE LOGITS
     tadi
    0.10
     aforementioned
    0.10
    åĪļæīį
    0.09
    å¦Ĥä¸Ĭ
    0.08
    ä¸Ĭæĸĩ
    0.08
     oben
    0.07
    ä¸Ĭè¿°
    0.07
     Guta
    0.07
    çĤ¹åĩ»éĺħ读åİŁæĸĩ
    0.07
    åīįè¿°
    0.07
    Activations Density 0.330%

    No Known Activations