© 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. 19270
    Prev
    Next
    INDEX
    Explanations

    here you will find

    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
     overly
    -0.06
    èIJį
    -0.05
    ç¸
    -0.05
    å·¥ä½ľè¦ģæ±Ĥ
    -0.05
    é£İå°ĺ
    -0.05
    ÑĤва
    -0.05
    vor
    -0.05
     sequ
    -0.05
    áĥĶáĥijáĥIJ
    -0.05
    å±Ĥ次
    -0.04
    POSITIVE LOGITS
    uluh
    0.07
     dã
    0.06
    indik
    0.06
    (\'
    0.06
    iral
    0.06
     Caff
    0.06
    renz
    0.06
    ç¥Ģ
    0.06
     ÑĪлÑı
    0.06
    ATUS
    0.06
    Activations Density 0.028%

    No Known Activations