© 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. 18809
    Prev
    Next
    INDEX
    Explanations

    will/would followed by action verb

    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
    oni
    -0.06
    acher
    -0.06
    они
    -0.06
    anan
    -0.06
    igit
    -0.05
    yr
    -0.05
    èµ°ä½İ
    -0.05
    enis
    -0.05
     seasons
    -0.05
     kond
    -0.05
    POSITIVE LOGITS
    å±ij
    0.06
    .da
    0.05
    anye
    0.05
     شأÙĨ
    0.05
    éĤij
    0.05
    à¸ģลาà¸ĩ
    0.05
     slur
    0.05
    稿
    0.05
    Ỽc
    0.05
    ledes
    0.05
    Activations Density 0.023%

    No Known Activations