© 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. 18792
    Prev
    Next
    INDEX
    Explanations

    byte, bit, pixel, molecule, cell, atom

    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
     groove
    -0.05
    anden
    -0.05
    ussen
    -0.05
    罡
    -0.05
    è§ĦåĪĻåĴĮ
    -0.05
    pane
    -0.05
     traduit
    -0.05
     plane
    -0.05
    çݯèĬĤ
    -0.05
    æĶ¶éĽĨåĴĮ
    -0.05
    POSITIVE LOGITS
    ãĥĢãĥ¼
    0.06
    utan
    0.06
    onton
    0.06
    ouw
    0.06
    ater
    0.06
    æĶ¹åıĺèĩªå·±
    0.06
    ihad
    0.06
    Æ°á»Ľi
    0.06
    綾
    0.06
    è¦ĸçĤ¹
    0.06
    Activations Density 0.044%

    No Known Activations