© 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. 20324
    Prev
    Next
    INDEX
    Explanations

    totaling or summing

    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
     Przez
    -0.06
    plo
    -0.06
    thew
    -0.06
    coder
    -0.06
    VRT
    -0.06
    ammu
    -0.06
    /loading
    -0.05
     бабÑĥ
    -0.05
    ä¸Ģä½ĵçļĦ
    -0.05
    odge
    -0.05
    POSITIVE LOGITS
    lich
    0.06
    tha
    0.06
    züge
    0.06
    Ñĥв
    0.06
    wards
    0.05
     bind
    0.05
    åĮ¹éħį
    0.05
    ycler
    0.05
    å¾Ģè¿Ķ
    0.05
     bound
    0.05
    Activations Density 0.009%

    No Known Activations