© 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. 19253
    Prev
    Next
    INDEX
    Explanations

    reach their potential

    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
    ÑģÑĮ
    -0.06
    aways
    -0.06
    IsNull
    -0.06
    ceptar
    -0.06
     Fisc
    -0.06
    æĹłç§ģ
    -0.06
    inst
    -0.06
     rave
    -0.06
    adoria
    -0.06
    æľīåı²
    -0.06
    POSITIVE LOGITS
    otto
    0.06
    оÑĤÑı
    0.06
    å¤©çľ¼
    0.05
    èĥĮæĻ¯ä¸ĭ
    0.05
    æ·¹
    0.05
    约å®ļ
    0.05
     spread
    0.05
    mute
    0.05
    lemi
    0.05
    fram
    0.05
    Activations Density 0.011%

    No Known Activations