© 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. 20024
    Prev
    Next
    INDEX
    Explanations

    CSS flexbox and grid layout

    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
     abat
    -0.06
    cole
    -0.06
    äºĨäºĭ
    -0.05
    æīĭä¸ŃçļĦ
    -0.05
    éĺģ
    -0.05
    paced
    -0.05
     styles
    -0.05
    EEP
    -0.05
    ÚĨÛĮ
    -0.05
    館
    -0.05
    POSITIVE LOGITS
    orum
    0.05
    hurt
    0.05
    isin
    0.05
    ä¸į大
    0.05
     зай
    0.05
    insen
    0.05
     primary
    0.05
    ì§ĪìĿĦ
    0.05
    强大
    0.05
     ey
    0.05
    Activations Density 0.006%

    No Known Activations