© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61775
    Prev
    Next
    INDEX
    Explanations

    stairs, escalators, ladders

    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
    elijke
    -0.07
    elijk
    -0.07
    eke
    -0.07
    avr
    -0.07
    ield
    -0.07
    壤
    -0.07
     WATCH
    -0.07
    ĥ
    -0.07
    æł¡åĽŃçݯå¢ĥ
    -0.07
    ervas
    -0.07
    POSITIVE LOGITS
     stairs
    0.10
     леÑģÑĤ
    0.10
    楼梯
    0.09
     stair
    0.09
    æī¶æīĭ
    0.08
    lift
    0.08
     Stufe
    0.08
     ascent
    0.08
    æĶĢåįĩ
    0.08
     vestib
    0.08
    Activations Density 0.026%

    No Known Activations