© 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. 18509
    Prev
    Next
    INDEX
    Explanations

    myths without substance

    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
     Facil
    -0.06
    ayne
    -0.06
    деми
    -0.06
    езде
    -0.06
    sled
    -0.06
    ä¸ĢæıIJ
    -0.06
    versa
    -0.06
    uris
    -0.06
    avern
    -0.06
    mira
    -0.06
    POSITIVE LOGITS
     non
    0.05
    æķ¬
    0.05
    æ´
    0.05
     "
    0.05
    gor
    0.05
     Inter
    0.05
     ·
    0.05
    缩
    0.05
    pot
    0.05
    _inter
    0.04
    Activations Density 0.011%

    No Known Activations