© 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. 13218
    Prev
    Next
    INDEX
    Explanations

    adapted, cloned, fighters, original

    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
    ละ
    -0.07
    umah
    -0.07
    imah
    -0.07
    umu
    -0.07
    è´Łè´£äººè¡¨ç¤º
    -0.06
    umas
    -0.06
    à¸Ļวà¸Ļ
    -0.06
    жи
    -0.06
    çļĦè¿Ļä¸Ģ
    -0.06
    åħ¬æĬ¥
    -0.06
    POSITIVE LOGITS
    éĢħ
    0.08
    ajor
    0.08
    nix
    0.07
    å¼łåĺ´
    0.07
    確ãģĭãģ«
    0.07
    Definitions
    0.07
    rd
    0.07
    |x
    0.07
    é²²
    0.06
    è¿ħ
    0.06
    Activations Density 0.005%

    No Known Activations