© 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. 19881
    Prev
    Next
    INDEX
    Explanations

    calculate least common multiple

    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
    åĬ¨äºĨ
    -0.06
    onder
    -0.05
    å®ĮåĸĦäºĨ
    -0.05
    ssize
    -0.05
    inton
    -0.05
    atego
    -0.05
    inkin
    -0.05
    rost
    -0.05
    adir
    -0.05
    arrants
    -0.05
    POSITIVE LOGITS
    out
    0.05
    jol
    0.05
     говоÑĢиÑĤÑģÑı
    0.05
    -out
    0.05
    æİ
    0.05
    ç¿»
    0.05
    çĩĥ
    0.05
    hammer
    0.05
    广大群ä¼Ĺ
    0.05
     sleeper
    0.05
    Activations Density 0.093%

    No Known Activations