© 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
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 18677
    Prev
    Next
    INDEX
    Explanations

    Explaining the neuron's behavior based on the provided lists:The neuron appears to be activated by words and phrases indicating the beginning or initial state of something, often followed by descriptions of actions or states

    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
    ring
    -0.05
    éĢļè¿ĩè¿Ļ次
    -0.05
    ibre
    -0.05
    asad
    -0.05
    ince
    -0.05
    enberg
    -0.05
    imed
    -0.05
     Zad
    -0.05
    rise
    -0.05
    å°ī
    -0.05
    POSITIVE LOGITS
    /sites
    0.06
    low
    0.06
     accord
    0.06
    lingen
    0.06
    Acc
    0.06
     accr
    0.06
    acc
    0.05
    æĪĸå¤ļ个
    0.05
    说æĪij
    0.05
    éĻįåΰ
    0.05
    Activations Density 0.009%

    No Known Activations