© 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. 19100
    Prev
    Next
    INDEX
    Explanations

    become skilled, live longer, understand better

    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
    ä½Ĩä¹Ł
    -0.06
    åį´ä¹Ł
    -0.06
     вÑģемÑĥ
    -0.06
    çĤľ
    -0.06
    ãģıãģłãģķãģĦãģŃ
    -0.05
    ê³łë¥¼
    -0.05
     *))
    -0.05
    ÏĦήÏģιο
    -0.05
    说å®ŀè¯Ŀ
    -0.05
    æĺ¯çĽ¸å½ĵ
    -0.05
    POSITIVE LOGITS
     more
    0.13
     более
    0.11
     closer
    0.10
    more
    0.10
    æĽ´æ·±
    0.10
     hơn
    0.10
     más
    0.10
     better
    0.10
    æĽ´åĬł
    0.10
    å¾ĹæĽ´
    0.10
    Activations Density 0.054%

    No Known Activations