© 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. 21957
    Prev
    Next
    INDEX
    Explanations

    numbers and the

    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
    opin
    -0.06
    ç«Ļä½į
    -0.05
    çĴ
    -0.05
     verv
    -0.05
    /IP
    -0.05
    èݲåŃIJ
    -0.05
    worthy
    -0.05
    ihar
    -0.05
     ten
    -0.05
     til
    -0.05
    POSITIVE LOGITS
    ))==
    0.06
    dq
    0.05
    ðŁĺĢ
    0.05
    RL
    0.05
    cling
    0.05
    utor
    0.05
    使çĶ¨æŶ
    0.05
    UTOR
    0.05
    tempt
    0.05
    dw
    0.05
    Activations Density 0.001%

    No Known Activations