© 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. 63032
    Prev
    Next
    INDEX
    Explanations

    chemical fragments and numbers

    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
    ä¸Ģåī¯
    -0.07
    /tty
    -0.07
    åĭ¾
    -0.06
    çĶ¨äºİ
    -0.06
    pass
    -0.06
    èĪĩ人
    -0.06
    unga
    -0.06
     vet
    -0.06
    _aliases
    -0.06
    pas
    -0.06
    POSITIVE LOGITS
    retch
    0.08
    å°ijèµ°
    0.07
    acle
    0.07
    hest
    0.07
    abee
    0.07
    ahari
    0.07
     пÑĢодÑĥ
    0.07
    Encoded
    0.07
    åŃĹåŀĭ
    0.07
     münchen
    0.07
    Activations Density 0.002%

    No Known Activations