© 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. 9763
    Prev
    Next
    INDEX
    Explanations

    inquiry or question posed

    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
    abu
    -0.09
    åħ¨éĥ¨è¯Ħ论
    -0.09
    edo
    -0.09
    åĴĮç¾İ
    -0.09
    fieldset
    -0.08
    ç½ijåıĭè¯Ħ论
    -0.08
    ornado
    -0.08
    缮ãģ§
    -0.08
    åĴĮç»´çĶŁç´ł
    -0.08
    ania
    -0.08
    POSITIVE LOGITS
    -
    0.06
    åı¯éĢīä¸Ń
    0.06
    “
    0.06
    ="
    0.05
    :
    0.05
     timely
    0.05
    .com
    0.05
    O
    0.05
     há»ıi
    0.05
     significant
    0.05
    Activations Density 0.004%

    No Known Activations