© 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. 20984
    Prev
    Next
    INDEX
    Explanations

    ine...ine... in

    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
    estar
    -0.06
    htag
    -0.06
    .sup
    -0.06
     replaced
    -0.05
    icare
    -0.05
    oland
    -0.05
    å¾ģæ±Ĥ
    -0.05
    θηÏĥη
    -0.05
    éijij
    -0.05
    åķĨä¸ļä¸Ńå¿ĥ
    -0.05
    POSITIVE LOGITS
    elit
    0.06
    UB
    0.06
     unto
    0.05
     Sight
    0.05
     Gord
    0.05
    åĪ°å¤§
    0.05
    å®ŀ
    0.05
    èĭ¥æĹł
    0.05
    交ç»Ļ
    0.05
    åĨ·
    0.05
    Activations Density 0.052%

    No Known Activations