© 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. 20765
    Prev
    Next
    INDEX
    Explanations

    materials, proteins, drugs, films

    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
     rival
    -0.06
    avorites
    -0.05
     bol
    -0.05
    finder
    -0.05
    urt
    -0.05
     b
    -0.04
    criptor
    -0.04
     dev
    -0.04
     jet
    -0.04
    ottes
    -0.04
    POSITIVE LOGITS
    гна
    0.07
    anos
    0.07
    ihkan
    0.07
     sindic
    0.06
    Ñİ
    0.06
    ãĤĪãģı
    0.06
    è±ģ
    0.06
    æ´Ľå¤«
    0.06
    masters
    0.06
    èĥ½æºIJå±Ģ
    0.06
    Activations Density 0.006%

    No Known Activations