© 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. 57343
    Prev
    Next
    INDEX
    Explanations

    publisher's series

    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
    epat
    -0.08
    ORIZED
    -0.08
     многим
    -0.08
    FOUND
    -0.07
    ÅĤÄĻ
    -0.07
     Berger
    -0.07
     Reit
    -0.07
    á»ģn
    -0.07
    åī¯å¤Ħéķ¿
    -0.07
    çĸ½
    -0.07
    POSITIVE LOGITS
     actual
    0.11
    å®ŀéĻħçļĦ
    0.10
    å®ŀéĻħæĥħåĨµ
    0.10
    å®ŀéĻħ
    0.09
    actual
    0.09
     itself
    0.09
    å®ŀéĻħæĵįä½ľ
    0.09
    çļĦå®ŀéĻħ
    0.08
    åľºä¸ĬçļĦ
    0.08
     themselves
    0.08
    Activations Density 0.414%

    No Known Activations