© 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. 22274
    Prev
    Next
    INDEX
    Explanations

    loan spell/deal

    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
    tle
    -0.06
    çĩİ
    -0.06
    Fatal
    -0.05
     ferma
    -0.05
    æĮīæ¯Ķä¾ĭ
    -0.05
    arnya
    -0.05
    wab
    -0.05
    Conf
    -0.05
    åħ·ä½ĵéĹ®é¢ĺ
    -0.05
    æľ¯ä¸Ń
    -0.05
    POSITIVE LOGITS
    åİ»çľĭçľĭ
    0.05
    inning
    0.05
    erez
    0.05
    à¹ģà¸Ĺà¹ī
    0.05
    æĥ³åĩº
    0.05
    ecast
    0.05
    empt
    0.05
    HAS
    0.05
     adapt
    0.05
    iance
    0.05
    Activations Density 0.008%

    No Known Activations