© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21589
    Prev
    Next
    INDEX
    Explanations

    + followed by another word

    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
    false
    -0.07
    true
    -0.06
    ty
    -0.06
    ti
    -0.06
    (false
    -0.06
     false
    -0.06
    False
    -0.06
     Ñģлизи
    -0.05
    å¿ĥå¦Ĥ
    -0.05
    ÐĶС
    -0.05
    POSITIVE LOGITS
    avin
    0.07
    rama
    0.06
    ç»ĦåIJĪ
    0.05
     cam
    0.05
    ä¹ĭ以
    0.05
    avings
    0.05
    leasing
    0.05
    éŁ³
    0.05
    loo
    0.05
     обÑĢаÑĤ
    0.05
    Activations Density 0.055%

    No Known Activations