© 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. 19109
    Prev
    Next
    INDEX
    Explanations

    date formats (MM/DD/YYYY, DD-MM-YYYY)

    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
    éļħ
    -0.06
    ator
    -0.05
    ow
    -0.05
    icul
    -0.05
    æĸĩåŃ¦å®¶
    -0.05
    è¯ģ
    -0.05
    yani
    -0.05
     Äijạo
    -0.05
     celebrity
    -0.05
    atelj
    -0.04
    POSITIVE LOGITS
    ...*
    0.07
    ible
    0.06
    룰
    0.06
    otton
    0.06
    ecek
    0.06
    »*
    0.06
     paral
    0.06
    asures
    0.06
    ata
    0.06
    IBLE
    0.06
    Activations Density 0.010%

    No Known Activations