© 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. 19348
    Prev
    Next
    INDEX
    Explanations

    names after titles or identifiers

    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
    ç»ıæµİæĮĩæłĩ
    -0.07
    labs
    -0.07
    ehm
    -0.07
    az
    -0.07
    è¿ĺæĺ¯è¦ģ
    -0.07
    elli
    -0.06
    åį´å¾Ī
    -0.06
    åĩłå¤§
    -0.06
    azo
    -0.06
    aur
    -0.06
    POSITIVE LOGITS
    尤为
    0.09
    è¿ĺ好
    0.08
    å°¤åħ¶
    0.08
     addirittura
    0.08
    سÙĬس
    0.07
    ãģłãģijãģ§ãĤĤ
    0.07
    åı£éķĩ
    0.07
    uper
    0.07
    å°Ĩä¸Ģ个
    0.07
    亦çĦ¶
    0.07
    Activations Density 0.213%

    No Known Activations