© 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. 20583
    Prev
    Next
    INDEX
    Explanations

    words spoken or written by someone

    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
    evin
    -0.06
    ppi
    -0.06
    andal
    -0.05
    å¯ĦãģĽ
    -0.05
     Walking
    -0.05
    åIJįåī¯åħ¶å®ŀ
    -0.05
    жÑĮÑı
    -0.05
    ends
    -0.05
    asy
    -0.05
     Sitz
    -0.05
    POSITIVE LOGITS
    æĿ
    0.06
    κÏģι
    0.06
    ersistent
    0.06
     exactly
    0.06
    ä½£
    0.05
     вÑģего
    0.05
    使çĶ¨
    0.05
    详æĥħ
    0.05
    åĭĭ
    0.05
    Exactly
    0.05
    Activations Density 0.496%

    No Known Activations