© 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. 51106
    Prev
    Next
    INDEX
    Explanations

    or vs and but

    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
    ujet
    -0.08
    agli
    -0.08
    aturi
    -0.07
    inge
    -0.07
    rama
    -0.07
    ãĥŃãĤ¹
    -0.07
    rapper
    -0.07
    queta
    -0.07
    immers
    -0.06
    rics
    -0.06
    POSITIVE LOGITS
    亦çĦ¶
    0.07
    Unhandled
    0.07
     versa
    0.07
    æĶ¾è¿ĩ
    0.07
     vice
    0.07
     keduanya
    0.07
    à°Łà°¿
    0.07
    两èĢħ
    0.07
    åĪ¹
    0.06
     unf
    0.06
    Activations Density 0.028%

    No Known Activations