© 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. 46111
    Prev
    Next
    INDEX
    Explanations

    words ending in -er or -or

    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
    ajt
    -0.07
    ä¾ĭ
    -0.07
    inga
    -0.06
    广
    -0.06
    umo
    -0.06
    rama
    -0.06
    é¢ĺå¹²
    -0.06
    æĪIJ羣
    -0.06
    æ²ģ
    -0.06
    ostal
    -0.06
    POSITIVE LOGITS
    ftar
    0.09
    ardini
    0.08
    uzzi
    0.08
    ansson
    0.07
    osexual
    0.07
    orius
    0.07
    ее
    0.07
    æĪij们å°Ĩåľ¨
    0.07
    ovol
    0.07
    icer
    0.07
    Activations Density 0.172%

    No Known Activations