© 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. 26179
    Prev
    Next
    INDEX
    Explanations

    speed limit

    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
    apid
    -0.08
    åįĥéĩij
    -0.08
    æĪIJåĬŁåIJİåį³åı¯
    -0.08
    çĽ¸å¯¹æ¹¿åº¦
    -0.08
    AYA
    -0.08
    注éĶĢå¤ĩæ¡Ī
    -0.08
    ä¸įæĦģ
    -0.08
     Camere
    -0.08
     Ambi
    -0.08
    ä¸įåºĶæ±Ĥ
    -0.07
    POSITIVE LOGITS
     limit
    0.08
    æŀģéĻIJ
    0.08
     limits
    0.08
     limiter
    0.07
    åıªèĥ½
    0.07
    éĻIJåĪ¶
    0.07
    åħīéĢŁ
    0.07
     limiting
    0.07
    éĢŁåº¦
    0.07
    éģµå®Ī
    0.07
    Activations Density 0.003%

    No Known Activations