© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17294
    Prev
    Next
    INDEX
    Explanations

    's or therefore followed by important

    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
    se
    -0.06
     se
    -0.06
    é½IJ
    -0.05
    List
    -0.05
    j
    -0.05
    éĥ½
    -0.05
    late
    -0.05
    WD
    -0.05
    DM
    -0.05
    ↵
    -0.05
    POSITIVE LOGITS
    пин
    0.07
     Borrow
    0.07
    énd
    0.06
    éľĢè¦ģæł¹æį®
    0.06
     vera
    0.06
    ÑģмоÑĤÑĢиÑĤе
    0.06
    rogen
    0.06
     заблÑĥ
    0.06
     Сод
    0.06
     borrow
    0.06
    Activations Density 0.001%

    No Known Activations