© 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. 18718
    Prev
    Next
    INDEX
    Explanations

    limits n

    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
    ity
    -0.08
    <tool_response>
    -0.07
    inet
    -0.07
    तर
    -0.07
    åĬŀåħ¬å®¶åħ·
    -0.07
    keer
    -0.07
    iness
    -0.07
    lm
    -0.07
    enho
    -0.07
    bane
    -0.07
    POSITIVE LOGITS
    ãĥ¬ãĥ¼ãĥĪ
    0.07
    æĽ²
    0.07
    æľīçļĦæŶåĢĻ
    0.07
    ä½İèĩ³
    0.06
    aisse
    0.06
    æŃ¤èµ·
    0.06
    Ãłng
    0.06
    aka
    0.06
    çĻ½çŁ³
    0.06
    ×ŀ×ķת
    0.06
    Activations Density 0.017%

    No Known Activations