© 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. 15206
    Prev
    Next
    INDEX
    Explanations

    is increasing. Tramadol is a synthetic opioid"

    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
    å¼ķ以为
    -0.08
    è´µå¦ĥ
    -0.08
    gard
    -0.08
    çĶ±åħ¶
    -0.07
    ä¹ĭä½Ļ
    -0.07
    uevo
    -0.07
    åĩºå½©
    -0.07
    resso
    -0.07
    ownt
    -0.07
    ertos
    -0.07
    POSITIVE LOGITS
    èĻ½çĦ¶åľ¨
    0.10
    èĻ½çĦ¶æĺ¯
    0.09
    erti
    0.08
    èĻ½çĦ¶
    0.07
    èĻ½
    0.07
    èĻ½çĦ¶æľī
    0.07
    åıªèĥ½åľ¨
    0.07
    åĽĽæµ·
    0.07
    çļĦåŃĺåľ¨
    0.07
    aroo
    0.07
    Activations Density 0.213%

    No Known Activations