© 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. 21952
    Prev
    Next
    INDEX
    Explanations

    behind or beneath

    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
    veau
    -0.08
    berman
    -0.08
    bedingt
    -0.08
     dÃłng
    -0.08
    rück
    -0.08
    abwe
    -0.08
    äºĪ以
    -0.07
    astic
    -0.07
    oyer
    -0.07
     outset
    -0.07
    POSITIVE LOGITS
    åIJ«ä¹ī
    0.09
    çļĦäººä¹Ł
    0.08
    éļIJèĹıçĿĢ
    0.08
    bones
    0.08
    ÙĬات
    0.07
     ÙĪبÙĬÙĨ
    0.07
    æ·±å±Ĥ
    0.07
    ings
    0.07
    è§Ħå¾ĭ
    0.07
    çĿĢçļĦ
    0.07
    Activations Density 0.008%

    No Known Activations