© 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. 20210
    Prev
    Next
    INDEX
    Explanations

    and

    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
    arest
    -0.06
     UNS
    -0.06
     teatr
    -0.05
    宣
    -0.05
    elij
    -0.05
    еÑī
    -0.05
    åĭĿè²ł
    -0.05
    leck
    -0.05
    æī¿è®¤
    -0.05
    ór
    -0.05
    POSITIVE LOGITS
    ä¼´
    0.06
    ?}",
    0.06
    kop
    0.05
    çĶļ
    0.05
    sville
    0.05
    bei
    0.05
     sheer
    0.05
    notice
    0.05
     Gee
    0.05
    rit
    0.05
    Activations Density 0.002%

    No Known Activations