© 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. 16956
    Prev
    Next
    INDEX
    Explanations

    manifest package

    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
    accordo
    -0.07
    ä»Ģä¹Īåij¢
    -0.06
    åij½çļĦ
    -0.06
    effectu
    -0.06
    اÙĤ
    -0.06
    raul
    -0.06
    levard
    -0.06
    rror
    -0.06
    大大å°ı
    -0.06
    çĦ¶å¤§
    -0.06
    POSITIVE LOGITS
    ÑģÑı
    0.08
    est
    0.06
    çļĦ
    0.06
    åĩºåİ»
    0.06
    yped
    0.06
    ulas
    0.06
    oria
    0.06
    ides
    0.05
    ed
    0.05
    im
    0.05
    Activations Density 0.012%

    No Known Activations