© 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. 8449
    Prev
    Next
    INDEX
    Explanations

    synonym, description, characteristics

    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
    çĦī
    -0.09
    ecd
    -0.08
    gie
    -0.08
    imore
    -0.08
    _=
    -0.07
    ä½ľæ³ķ
    -0.07
    åij±
    -0.07
    jön
    -0.07
    spflicht
    -0.07
    *_
    -0.07
    POSITIVE LOGITS
    çļĦæĦıæĢĿ
    0.08
     synonym
    0.07
    chado
    0.07
     synonyms
    0.07
    è¯ij为
    0.06
    形容
    0.06
    è¯łéĩĬ
    0.06
     characteristics
    0.06
    訳
    0.06
     description
    0.06
    Activations Density 0.033%

    No Known Activations