© 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. 18851
    Prev
    Next
    INDEX
    Explanations

    cryptographic library, running, species, class

    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
    æµ·æ¶Ľ
    -0.08
    UES
    -0.08
    æ¶Ľ
    -0.07
    ebr
    -0.07
    raj
    -0.07
    غر
    -0.07
    éļıåį³
    -0.07
    è¦ģæ±Ĥåħ¶
    -0.07
    çŁ¥åħ¶
    -0.07
    太éĥİ
    -0.06
    POSITIVE LOGITS
    claimed
    0.08
    azit
    0.08
     finalement
    0.07
    chet
    0.07
    rome
    0.07
    ancel
    0.07
    antemente
    0.07
    æľĢç»Ī
    0.07
    RelativeTo
    0.07
    驱
    0.07
    Activations Density 0.004%

    No Known Activations