© 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. 21755
    Prev
    Next
    INDEX
    Explanations

    linking phrases

    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
    rochen
    -0.06
    ìĸ¸
    -0.06
    ancar
    -0.06
    reno
    -0.06
     unfavor
    -0.06
    mand
    -0.06
    ert
    -0.06
    ÑįÑĪ
    -0.06
    engel
    -0.06
    rear
    -0.06
    POSITIVE LOGITS
     sounding
    0.06
     harap
    0.05
    å¾Ģ
    0.05
    éĻ·
    0.05
     val
    0.05
     str
    0.05
    çľĭä¸Ĭåİ»
    0.05
    é¡¿
    0.05
    icum
    0.05
     mol
    0.05
    Activations Density 0.001%

    No Known Activations