© 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. 45351
    Prev
    Next
    INDEX
    Explanations

    Studybay function php

    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
    ä¸įèĩªç¦ģ
    -0.09
     вÑħод
    -0.08
    brig
    -0.07
    ä¸īåħ«
    -0.07
     impost
    -0.07
    大åĬĽå¼ĺæī¬
    -0.07
    voud
    -0.07
    (TM
    -0.07
    ggi
    -0.07
    trup
    -0.07
    POSITIVE LOGITS
    çĽijçIJĨå·¥ç¨ĭå¸Ī
    0.07
     Dere
    0.06
    mime
    0.06
    宵
    0.06
    bourg
    0.06
    .uni
    0.06
    éĢĶ
    0.06
    å¢ĥ
    0.06
    ocket
    0.06
    _SYMBOL
    0.06
    Activations Density 0.003%

    No Known Activations