© 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. 41115
    Prev
    Next
    INDEX
    Explanations

    Compilation, branding, Terminator, Lucha Libre AAA

    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
    att
    -0.07
    agna
    -0.06
    ogan
    -0.06
    åĽŀ
    -0.06
    åº
    -0.06
    åĤ¬
    -0.06
    yre
    -0.05
    åİŁåĽł
    -0.05
    éķĩ
    -0.05
    使çĶ¨äºĨ
    -0.05
    POSITIVE LOGITS
    ç®Ģç®Ģåįķ
    0.09
    åĩŃåĢŁåħ¶
    0.08
    upert
    0.08
    лее
    0.08
    лак
    0.08
    åī¯çľģéķ¿
    0.08
    Ïįν
    0.08
    缸åħ³éĹ®çŃĶ
    0.08
    è¿ĺæľīä¸ĢçĤ¹
    0.08
    ìĸ
    0.07
    Activations Density 0.003%

    No Known Activations