© 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. 2521
    Prev
    Next
    INDEX
    Explanations

    word fragments ending in suffixes like "-ed", "-es", "-ation", or "-ing" that form past participles or noun forms

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
    æŁĶæĥħ
    -0.07
    ç¶
    -0.06
    ä½Ĩæĺ¯åį´
    -0.06
    ä½įåŃIJ
    -0.06
    çµ
    -0.06
    )?$
    -0.06
    大æ´ĭ
    -0.06
    汶
    -0.06
    转载èĩª
    -0.06
     wor
    -0.06
    POSITIVE LOGITS
    åīįè¿°
    0.10
    _via
    0.10
     \`
    0.08
    éĢļè¿ĩ以ä¸Ĭ
    0.08
    umi
    0.08
     \''
    0.08
    大å¹ħæıIJåįĩ
    0.08
    èij±å§ľ
    0.07
    etu
    0.07
    ç¾İçijŀ
    0.07
    Activations Density 0.000%

    No Known Activations