© 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. 23345
    Prev
    Next
    INDEX
    Explanations

    all others

    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
     ones
    -0.09
    bsp
    -0.08
    /unit
    -0.08
    ona
    -0.08
    appa
    -0.08
    ardini
    -0.07
    uar
    -0.07
    ä¸Ńä¹ĭ
    -0.07
    /course
    -0.07
    edula
    -0.07
    POSITIVE LOGITS
    quarters
    0.07
     stages
    0.07
     phases
    0.07
    åıijå±ķéĺ¶æ®µ
    0.07
     species
    0.07
    维度
    0.07
    éĺ¶æ®µ
    0.06
    è¯Ńç§į
    0.06
     iteration
    0.06
    è¿ĽåĪ¶
    0.06
    Activations Density 0.777%

    No Known Activations