© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19843
    Prev
    Next
    INDEX
    Explanations

    allodynia, hypersensitivity, hyperresponsiveness

    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
     Acompan
    -0.07
    ROC
    -0.06
     Acomp
    -0.06
    æľĿé£Ł
    -0.06
     desag
    -0.06
    åģı
    -0.06
    æĭ¥æĬ¤
    -0.06
    ivy
    -0.06
     ess
    -0.06
    schlag
    -0.05
    POSITIVE LOGITS
     ble
    0.05
     en
    0.05
    pun
    0.05
    imens
    0.05
    çļĦçī¹æ®Ĭ
    0.05
    éľľ
    0.05
     rates
    0.05
     PEN
    0.05
    èį
    0.05
    çĥĪ
    0.05
    Activations Density 0.004%

    No Known Activations