© 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. 20918
    Prev
    Next
    INDEX
    Explanations

    season numbers and related content

    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
    illot
    -0.06
    åĮķ
    -0.05
    ÙĬا
    -0.05
     famously
    -0.05
     Edwin
    -0.05
    sequ
    -0.05
     tÃŃ
    -0.05
    åIJ¸æĶ¶
    -0.05
    ammel
    -0.05
    çam
    -0.05
    POSITIVE LOGITS
    å°ĨçIJĥ
    0.06
     vừa
    0.06
    alk
    0.06
    obo
    0.06
     ÐĺзÑĥ
    0.06
     classifica
    0.06
    ç±ģ
    0.06
    aiss
    0.06
    åħ¬æīĢ
    0.05
    å®ģæµ·
    0.05
    Activations Density 0.084%

    No Known Activations