© 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. 51579
    Prev
    Next
    INDEX
    Explanations

    division into parts or phases

    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
    eces
    -0.08
    hofer
    -0.08
    äºī
    -0.07
    à¸Ķุ
    -0.07
    åį´æĹłæ³ķ
    -0.07
    ILON
    -0.07
    imun
    -0.07
    plice
    -0.07
    åį´ä¸įèĥ½
    -0.07
    manent
    -0.07
    POSITIVE LOGITS
    åīįèĢħ
    0.07
    åºĶéħ¬
    0.07
    åģļ好
    0.07
    两大类
    0.07
    åħĪ
    0.06
    åīįåįĬ
    0.06
    è¶Ĭèµ°è¶Ĭ
    0.06
    onte
    0.06
    åįģäºĶ
    0.06
     extensive
    0.06
    Activations Density 0.041%

    No Known Activations