© 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. 18270
    Prev
    Next
    INDEX
    Explanations

    mathematical ellipsis

    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
    oor
    -0.06
     Colomb
    -0.06
    коÑĤа
    -0.06
    endis
    -0.06
    urile
    -0.06
    chio
    -0.06
    对åħ¬åı¸
    -0.06
    éĻIJãĤĬ
    -0.06
    ieber
    -0.05
    ritel
    -0.05
    POSITIVE LOGITS
    æĭħ
    0.06
    ÃŃm
    0.05
    ä¹Łä¸įä¸Ģå®ļ
    0.05
    顯
    0.05
    å½¢
    0.05
    æĺ¯åIJ§
    0.05
     nth
    0.05
    è¾IJå°Ħ
    0.04
    ä½Ľç¥ĸ
    0.04
    çĶŁéķ¿
    0.04
    Activations Density 0.011%

    No Known Activations