© 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. 43404
    Prev
    Next
    INDEX
    Explanations

    words ending in 'st'

    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
    lsen
    -0.09
    ãģ¹ãģį
    -0.09
    à§įস
    -0.09
    incinnati
    -0.08
    ìĦľëĬĶ
    -0.08
    itäts
    -0.08
    thest
    -0.08
    thes
    -0.08
    ndon
    -0.08
    หà¸Ļà¹īาà¸Ļีà¹ī
    -0.08
    POSITIVE LOGITS
    evens
    0.14
    ewart
    0.13
    andard
    0.12
    ANDARD
    0.12
    ablish
    0.12
    urgeon
    0.11
    غرÙĤ
    0.10
    /testify
    0.10
    ئÙĨاÙģ
    0.10
    udios
    0.10
    Activations Density 1.095%

    No Known Activations