© 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. 20276
    Prev
    Next
    INDEX
    Explanations

    stop, off, loss, time

    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
    awning
    -0.06
    çģ£
    -0.05
    åĺĽ
    -0.05
    èİŀ
    -0.05
    å±ŀ
    -0.05
     raus
    -0.05
    tio
    -0.05
     pis
    -0.05
    aup
    -0.05
     temu
    -0.05
    POSITIVE LOGITS
    ä½Ĩ并ä¸į
    0.07
    并æıIJä¾Ľ
    0.06
    usiai
    0.06
    è¯ī
    0.06
     sufficiently
    0.06
     unfavor
    0.06
    ingly
    0.06
    ä½Ĩåį´
    0.06
    логи
    0.06
    ä½Ĩ没æľī
    0.05
    Activations Density 0.085%

    No Known Activations