© 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. 1113
    Prev
    Next
    INDEX
    Explanations

    coupe or ubuntu

    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
    /location
    -0.07
    è¿Ľå±ķæĥħåĨµ
    -0.06
    *K
    -0.06
    çļĦæŶåĢĻä¼ļ
    -0.06
    iners
    -0.06
    stech
    -0.06
    以åıĬåľ¨
    -0.06
    åľ°å¸¦
    -0.06
    fen
    -0.06
    çŁ£
    -0.06
    POSITIVE LOGITS
    amá
    0.08
    ptos
    0.08
    æ¦Ħ
    0.08
    á»ĩp
    0.08
    æ§
    0.07
    artal
    0.07
     Mounted
    0.07
    Mounted
    0.07
    berger
    0.07
    ington
    0.07
    Activations Density 0.004%

    No Known Activations