© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17793
    Prev
    Next
    INDEX
    Explanations

    ranged attacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    'o
    -0.07
    æľªåĪ°
    -0.06
    yu
    -0.05
     doux
    -0.05
    ici
    -0.05
     least
    -0.05
    ibs
    -0.05
    ilton
    -0.05
    odo
    -0.05
    yun
    -0.05
    POSITIVE LOGITS
    wegen
    0.06
    versch
    0.06
     ultim
    0.06
    ä¸ĢéĹ®
    0.06
     modeller
    0.06
    quet
    0.06
    ä¸Ĭæīĭ
    0.06
     bizar
    0.06
    katan
    0.06
    pper
    0.06
    Activations Density 0.014%

    No Known Activations