© 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. 19202
    Prev
    Next
    INDEX
    Explanations

    quoted strings and delimiters

    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
    -kit
    -0.07
    tui
    -0.07
    abet
    -0.07
     tame
    -0.07
    Ops
    -0.07
     lẫn
    -0.06
    _OPERATION
    -0.06
    è¦ģä¸įçĦ¶
    -0.06
    ulary
    -0.06
    ä¸ĭæĿ¥äºĨ
    -0.06
    POSITIVE LOGITS
    å¾ĺ
    0.08
    æĦŁãģĺãģ§
    0.08
    osso
    0.07
    arf
    0.07
    æĦıæĢĿ
    0.07
    åħ³éĶ®æĺ¯
    0.07
    è¿ĻéľĢè¦ģ
    0.07
    _container
    0.07
    itim
    0.07
    å¿ħ须以
    0.07
    Activations Density 0.004%

    No Known Activations