© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19461
    Prev
    Next
    INDEX
    Explanations

    intuition or instinct

    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
    uar
    -0.06
    rup
    -0.05
    orrent
    -0.05
    chant
    -0.05
    ä¸įè¾¾
    -0.05
     ÐłÐµÑĩÑĮ
    -0.05
     absent
    -0.05
    ropa
    -0.05
    ema
    -0.05
    urit
    -0.05
    POSITIVE LOGITS
    åģļæ³ķ
    0.06
    _prediction
    0.06
     prediction
    0.06
    ä½ľæ³ķ
    0.06
    é¢Ħæµĭ
    0.06
    itse
    0.06
    ç»ĵ论
    0.06
     predictions
    0.06
     predicting
    0.05
    çµIJè«ĸ
    0.05
    Activations Density 0.004%

    No Known Activations