© 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. 19683
    Prev
    Next
    INDEX
    Explanations

    genuine or abnormal

    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
     ÙĨزد
    -0.05
    ç¾İç¾İ
    -0.05
     shelter
    -0.05
    logged
    -0.05
     ang
    -0.05
    æĻ
    -0.05
     enough
    -0.05
     condizion
    -0.05
     packed
    -0.05
    æİ
    -0.05
    POSITIVE LOGITS
     genuinely
    0.09
     genuine
    0.08
     truly
    0.07
    åĪ«æľī
    0.06
    enuine
    0.06
     Genuine
    0.06
    ernal
    0.06
     ØŃÙĤÙĬÙĤÙĬØ©
    0.06
    lech
    0.06
    åĪ«æĹł
    0.06
    Activations Density 0.099%

    No Known Activations