© 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. 20684
    Prev
    Next
    INDEX
    Explanations

    occurrence of "first time"

    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
    illot
    -0.07
     kontakte
    -0.07
     rectific
    -0.07
    pris
    -0.06
     succes
    -0.06
    дин
    -0.06
    umfang
    -0.06
    odr
    -0.06
    çļĦäºĭäºĨ
    -0.06
     dw
    -0.06
    POSITIVE LOGITS
    apper
    0.05
     de
    0.05
    ents
    0.05
    isci
    0.05
    rox
    0.05
    ere
    0.05
    0.05
    aff
    0.05
     collo
    0.05
    ress
    0.05
    Activations Density 0.013%

    No Known Activations