© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18967
    Prev
    Next
    INDEX
    Explanations

    without having to

    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
    azzino
    -0.06
     silakan
    -0.06
    blings
    -0.06
    (integer
    -0.05
    ç»Ĩå°ı
    -0.05
     tills
    -0.05
    亦æľī
    -0.05
    веÑĢÑĪен
    -0.05
    ayo
    -0.05
    terior
    -0.05
    POSITIVE LOGITS
    ver
    0.06
    æĦŁåĪ°
    0.06
     instead
    0.05
    igm
    0.05
    amer
    0.05
    æĻ¨æĬ¥
    0.05
    å®ļåĪ¶
    0.05
    ÛĮار
    0.05
     Ver
    0.05
    nger
    0.05
    Activations Density 0.001%

    No Known Activations