© 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. 18957
    Prev
    Next
    INDEX
    Explanations

    memory cell area

    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
    пл
    -0.07
    fone
    -0.07
    ç´¡
    -0.06
    lesh
    -0.06
     distanci
    -0.06
    ãĥĭãĥ¼
    -0.06
    erness
    -0.06
    ewe
    -0.06
    otions
    -0.06
     expos
    -0.05
    POSITIVE LOGITS
    è¨Ģ
    0.06
    æķĪ
    0.06
    åĪ©
    0.06
    主åĬĽ
    0.05
    æĬŀ
    0.05
    è½½
    0.05
    zor
    0.05
    éĩĮæĺĤ
    0.05
    ALIGN
    0.05
    alis
    0.05
    Activations Density 0.060%

    No Known Activations