© 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. 18340
    Prev
    Next
    INDEX
    Explanations

    has/have/been followed by a verb/adjective

    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
    bauer
    -0.08
    orial
    -0.07
    agni
    -0.07
    ç²¹
    -0.07
    bote
    -0.06
    bem
    -0.06
     îÈĻi
    -0.06
    prung
    -0.06
    fél
    -0.06
    -Trump
    -0.06
    POSITIVE LOGITS
    ↵
    0.05
    0.05
    ens
    0.05
    ,
    0.05
     N
    0.05
    equ
    0.05
    hi
    0.05
     new
    0.05
    hel
    0.05
     d
    0.05
    Activations Density 0.158%

    No Known Activations