© 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. 16979
    Prev
    Next
    INDEX
    Explanations

    if or whether

    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
    ey
    -0.06
    ãģĤãĤĭ
    -0.05
    unk
    -0.05
    à¸ĩ
    -0.05
     seemed
    -0.05
    unn
    -0.05
    ear
    -0.05
    ins
    -0.05
     inexp
    -0.05
    ep
    -0.05
    POSITIVE LOGITS
     facto
    0.07
    åĽĽå°Ħ
    0.06
    oku
    0.06
    à¸Ľà¸£à¸°à¸Ĭ
    0.06
    bidden
    0.06
    PRECATED
    0.06
    équip
    0.06
    itats
    0.06
    çĪ±ç¾İ
    0.06
    اÙĦات
    0.06
    Activations Density 0.015%

    No Known Activations