© 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. 22973
    Prev
    Next
    INDEX
    Explanations

    addressing group/leader/friend

    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
    åĴĮä¸į足
    -0.08
    .argv
    -0.08
    以åıĬå¦Ĥä½ķ
    -0.07
    åĴĮæĶ¹åĸĦ
    -0.07
    åı«å¥¹
    -0.07
    åĬłæĭ¿å¤§
    -0.07
    å°Ķå¾·
    -0.07
    igue
    -0.07
    她便
    -0.07
     themselves
    -0.07
    POSITIVE LOGITS
    arl
    0.07
    级çļĦ
    0.07
     Æ¡i
    0.07
    å¤ļ大
    0.06
    pton
    0.06
    otte
    0.06
    ëĭ¤ë©´
    0.06
    веÑĤа
    0.06
    级以ä¸Ĭ
    0.06
    plier
    0.06
    Activations Density 0.043%

    No Known Activations