© 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. 17413
    Prev
    Next
    INDEX
    Explanations

    according to their

    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
    bery
    -0.06
     whatever
    -0.05
    иÑĤо
    -0.05
    pj
    -0.05
    olos
    -0.05
    涯
    -0.05
    çĬ¶åĨµ
    -0.05
    igraf
    -0.05
    æ¶Ĥ鸦
    -0.05
    BG
    -0.05
    POSITIVE LOGITS
     Sus
    0.06
    æ°ij
    0.05
     sus
    0.05
    /pm
    0.05
    ÑĨиона
    0.05
     _______,
    0.05
    对
    0.05
    lave
    0.05
    æĭĤ
    0.05
    éĿ©
    0.05
    Activations Density 0.041%

    No Known Activations