© 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. 56226
    Prev
    Next
    INDEX
    Explanations

    introduces reasons

    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
    è¿Ļç§į人
    -0.08
    iel
    -0.08
    åIJĮä¸Ģ
    -0.08
    åIJĮä¸Ģ个
    -0.07
    对äºİéĤ£äºĽ
    -0.07
    .each
    -0.07
    els
    -0.07
    opil
    -0.07
    راج
    -0.07
    ãĥĥãĤ»
    -0.07
    POSITIVE LOGITS
    yntax
    0.07
    ä¸įæĹ©
    0.07
     pina
    0.06
    yne
    0.06
    æĮĤäºĨ
    0.06
    ின
    0.06
    eded
    0.06
    roids
    0.06
    è¯ģåĪ¸èĤ¡ä»½æľīéĻIJåħ¬åı¸
    0.06
    enzio
    0.06
    Activations Density 0.001%

    No Known Activations