© 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. 56586
    Prev
    Next
    INDEX
    Explanations

    halophilic, psychrophilic, adapted, plasticity

    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
    符
    -0.08
    uctose
    -0.08
    åĬĽåº¦
    -0.07
    agerie
    -0.07
    å¨ģä¿¡
    -0.07
    æŃ¢
    -0.07
    åĪĨéĩı
    -0.07
    çļĦåĬĽåº¦
    -0.07
    æĬ¡
    -0.07
    èĿ´èĿ¶
    -0.07
    POSITIVE LOGITS
    éĢĤåºĶèĥ½åĬĽ
    0.14
    éĢĤåºĶæĢ§
    0.13
    éĢĤåºĶ
    0.13
    éĢĤåºĶäºĨ
    0.13
     adapted
    0.12
     adaptations
    0.12
     thrive
    0.12
     adaptation
    0.12
    èĥ½éĢĤåºĶ
    0.11
    éģ©æĩī
    0.11
    Activations Density 0.087%

    No Known Activations