© 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. 61858
    Prev
    Next
    INDEX
    Explanations

    equality, order, or mapping

    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
    ä¸įåĪ©
    -0.09
    çŃīéĩįçĤ¹
    -0.08
    irro
    -0.07
    ETTA
    -0.07
     #=>
    -0.07
    ìĬ¤íģ¬
    -0.07
    оÑĢоÑĤ
    -0.07
    çĪ¶æ¯įçļĦ
    -0.07
    .parents
    -0.07
    ikota
    -0.07
    POSITIVE LOGITS
    碰
    0.08
     pleasantly
    0.08
    jom
    0.08
    çijľ
    0.07
    å¢
    0.07
    /IP
    0.07
    ç¡Ģ
    0.07
    åĨħåIJ«
    0.06
    jem
    0.06
    妮
    0.06
    Activations Density 0.023%

    No Known Activations