© 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. 19875
    Prev
    Next
    INDEX
    Explanations

    present invention

    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
    atem
    -0.07
    åĪĩãĤĭ
    -0.07
    çijŀå®ī
    -0.06
    apas
    -0.06
    hir
    -0.06
    åıĺèī²
    -0.06
    ærer
    -0.06
    æ¡ĪçĶ±
    -0.06
    gable
    -0.06
     Aide
    -0.06
    POSITIVE LOGITS
     fis
    0.06
    è·¨
    0.06
    esu
    0.05
     remote
    0.05
     IT
    0.05
     Inter
    0.05
     local
    0.05
     вÑĭп
    0.05
     inter
    0.05
    龸
    0.05
    Activations Density 0.014%

    No Known Activations