© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19487
    Prev
    Next
    INDEX
    Explanations

    automatically performed actions

    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
    ic
    -0.06
    est
    -0.05
    atos
    -0.05
    happy
    -0.05
     `
    -0.05
    esk
    -0.05
    un
    -0.05
    éģĤ
    -0.05
    Gro
    -0.05
    æĵį
    -0.05
    POSITIVE LOGITS
    OrCreate
    0.07
    aling
    0.07
    nieuw
    0.07
     terça
    0.07
    çľ·
    0.06
    ÑħодÑıÑĤ
    0.06
    หรีà¹Ī
    0.06
    .CreateInstance
    0.06
    .parseFloat
    0.06
    ãĢĤâĢ»
    0.06
    Activations Density 0.011%

    No Known Activations