© 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. 48641
    Prev
    Next
    INDEX
    Explanations

    numeric ranges and comparisons

    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
    #w
    -0.08
    Trivia
    -0.08
    steen
    -0.07
     KV
    -0.07
    æīĢå±ķ示
    -0.07
    ahanan
    -0.07
    remen
    -0.07
    azes
    -0.07
    éĢ¼
    -0.07
    bers
    -0.07
    POSITIVE LOGITS
    çīĪæĿĥæīĢæľī
    0.07
    éĩijéĵ¶
    0.06
     pulp
    0.06
    ecil
    0.06
    åľºä¸ĬçļĦ
    0.06
     gen
    0.06
     turno
    0.06
    å¦Ĥä¸Ģ
    0.06
     PubMed
    0.06
    åĬłå¿«åıijå±ķ
    0.06
    Activations Density 0.773%

    No Known Activations