© 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. 61563
    Prev
    Next
    INDEX
    Explanations

    sometimes

    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
     presumably
    -0.14
     likely
    -0.12
     hopefully
    -0.12
     probably
    -0.11
    likely
    -0.10
    å¾Īåı¯èĥ½
    -0.10
     provavelmente
    -0.09
     probablemente
    -0.09
     Likely
    -0.08
    hopefully
    -0.08
    POSITIVE LOGITS
    çĶļèĩ³ä¼ļ
    0.14
     addirittura
    0.14
    íķĺ기ëıĦ
    0.14
     бÑĭваеÑĤ
    0.13
     sogar
    0.13
    çĶļèĩ³æĺ¯
    0.13
     persino
    0.12
    çĶļèĩ³
    0.12
    çĶļèĩ³è¿ŀ
    0.11
    çĶļèĩ³åľ¨
    0.11
    Activations Density 0.075%

    No Known Activations