© 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. 19353
    Prev
    Next
    INDEX
    Explanations

    end punctuation and specialized terms

    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
    ikian
    -0.09
    cript
    -0.08
    adoo
    -0.08
    uson
    -0.08
    ibbon
    -0.08
    _ONCE
    -0.08
    estan
    -0.08
     reconna
    -0.08
    izie
    -0.07
    ÃĶNG
    -0.07
    POSITIVE LOGITS
     Doma
    0.07
    è¿Ļåľ¨
    0.06
    ause
    0.06
    ä½ķåĨµ
    0.06
    å¾®å¦Ļ
    0.06
    贯穿äºİ
    0.06
    åºĶçĶ¨äºİ
    0.05
    rase
    0.05
    plex
    0.05
    phy
    0.05
    Activations Density 0.562%

    No Known Activations