© 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. 15748
    Prev
    Next
    INDEX
    Explanations

    subscripts and indexing (a_i, x_1)

    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
     Bom
    -0.06
    åѦä¸İ
    -0.06
    æķ´æķ´
    -0.06
    oral
    -0.05
    cons
    -0.05
    OK
    -0.05
    åİ
    -0.05
     rend
    -0.05
    hum
    -0.05
    åħĥ宵
    -0.05
    POSITIVE LOGITS
    gis
    0.09
    izan
    0.09
    çĦ¡äºº
    0.08
    emain
    0.08
    etti
    0.08
    kens
    0.08
    �t
    0.08
    esub
    0.08
    æŃ·
    0.08
     EUROP
    0.08
    Activations Density 0.082%

    No Known Activations