© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16809
    Prev
    Next
    INDEX
    Explanations

    torture and torment

    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
    à¹Ģà¸Ļืà¹īà¸Ń
    -0.06
    å¸ļ
    -0.06
    engen
    -0.06
    åĩĨ
    -0.06
    unn
    -0.06
    embro
    -0.06
    infile
    -0.06
    mä
    -0.06
    eer
    -0.06
     genomen
    -0.06
    POSITIVE LOGITS
     torture
    0.06
     tortured
    0.05
    è¡Įä¹ĭæľīæķĪçļĦ
    0.05
    èĥ½å¤Łå¯¹
    0.05
    设æ³ķ
    0.05
    cing
    0.05
     chambers
    0.05
    ievo
    0.05
    为ä»Ģä¹Īåij¢
    0.05
     dare
    0.05
    Activations Density 0.008%

    No Known Activations