© 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. 19755
    Prev
    Next
    INDEX
    Explanations

    Each method has

    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
    rut
    -0.06
    indir
    -0.06
    astr
    -0.06
    âĢİ
    -0.06
    ERA
    -0.06
    -ver
    -0.06
     comun
    -0.06
    å¤ĸéľ²
    -0.06
    ä¸įåIJĮç¨ĭ度
    -0.05
    ehu
    -0.05
    POSITIVE LOGITS
    à¹Ģà¸Īาะ
    0.06
    å¹´çļĦæŶéĹ´
    0.06
    orsch
    0.05
    大åĬĽåıijå±ķ
    0.05
    éĶµ
    0.05
     expanded
    0.05
    غة
    0.05
    rong
    0.05
    tragen
    0.05
    ÅĤada
    0.05
    Activations Density 0.009%

    No Known Activations