© 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. 22945
    Prev
    Next
    INDEX
    Explanations

    purchase, release, acquire, programming, submission

    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
    åı·ä»¤
    -0.08
    Ñģпол
    -0.07
    çİĭæ°ı
    -0.07
     à¸ķุล
    -0.07
    eton
    -0.07
    ARRIER
    -0.07
    inode
    -0.07
     berc
    -0.07
    hana
    -0.07
    eward
    -0.07
    POSITIVE LOGITS
    vol
    0.07
    .Generic
    0.06
    æĺŁæĺŁ
    0.06
    å¯¹çĽ¸åħ³
    0.06
    Es
    0.06
    cel
    0.06
    leo
    0.06
    lesi
    0.06
    zan
    0.06
     anz
    0.06
    Activations Density 0.329%

    No Known Activations