© 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. 3154
    Prev
    Next
    INDEX
    Explanations

    length and distance

    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
     állapot
    -0.07
    åīįåįģ
    -0.07
    aint
    -0.07
    ä¸Ģçīĩçīĩ
    -0.07
    ä¸įæĹ©
    -0.07
    ellini
    -0.07
    ä¸įåłª
    -0.07
    æŀĹä¸Ń
    -0.07
    çĬ¶æħĭãģ§
    -0.06
     heav
    -0.06
    POSITIVE LOGITS
    æľĢéķ¿çļĦ
    0.12
    è¶Ĭéķ¿
    0.11
    æľĢçŁŃ
    0.10
     length
    0.10
     longest
    0.10
    éķ¿åº¦
    0.10
     shortest
    0.09
     distance
    0.09
     Ø·ÙĪÙĦ
    0.09
     Length
    0.09
    Activations Density 0.034%

    No Known Activations