© 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. 40460
    Prev
    Next
    INDEX
    Explanations

    simple questions or explanations

    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
    éĤ£æĺ¯åĽłä¸º
    -0.08
    ingue
    -0.07
    illac
    -0.07
    amore
    -0.07
    æľªå¿ħ
    -0.07
    adaran
    -0.07
    itants
    -0.07
    artisan
    -0.07
    æľīåħ³è´Łè´£äºº
    -0.07
    estens
    -0.07
    POSITIVE LOGITS
     straightforward
    0.10
    åį³åı¯å®ĮæĪIJ
    0.08
    并ä¸įéļ¾
    0.08
    åıªè¦ģåľ¨
    0.08
    çĨŁ
    0.07
    èĢĮå·²
    0.07
    ä¸įéļ¾
    0.07
    åıªè¦ģ
    0.07
    å°±æĺ¯å°Ĩ
    0.07
    ()}
    0.07
    Activations Density 0.040%

    No Known Activations