© 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. 20848
    Prev
    Next
    INDEX
    Explanations

    drivers, company, people, seeker

    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
     Te
    -0.06
     te
    -0.06
    te
    -0.05
     tra
    -0.05
    need
    -0.05
    éĢĶ
    -0.05
     ve
    -0.05
     Dem
    -0.05
     rum
    -0.05
     complex
    -0.05
    POSITIVE LOGITS
    ;break
    0.06
    acca
    0.06
    arrass
    0.06
    ...”
    0.06
    æķ²
    0.06
    ...\
    0.06
    ESC
    0.06
    fino
    0.06
     endorsed
    0.06
     riêng
    0.06
    Activations Density 0.035%

    No Known Activations