© 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. 21981
    Prev
    Next
    INDEX
    Explanations

    SQL table and column names

    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
    usher
    -0.05
    éĨīéħĴ
    -0.05
    ingen
    -0.05
    orman
    -0.05
     nur
    -0.05
     attr
    -0.05
    å°Ĩ该
    -0.05
    imest
    -0.05
    lse
    -0.05
    åı²
    -0.05
    POSITIVE LOGITS
     Nationwide
    0.06
    ä¸ĩåıĺ
    0.06
     Deal
    0.06
    жÑĮ
    0.06
    åįĥæĸ¤
    0.06
     Ðķди
    0.06
    éļľ
    0.05
    olics
    0.05
     Albany
    0.05
    Deal
    0.05
    Activations Density 0.078%

    No Known Activations