© 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. 18380
    Prev
    Next
    INDEX
    Explanations

    string manipulation functions

    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
    iori
    -0.06
    Ĥ
    -0.06
    stairs
    -0.06
     ngũ
    -0.06
    zá
    -0.06
    边走
    -0.06
    ysi
    -0.05
    rezza
    -0.05
    ubuntu
    -0.05
    éľī
    -0.05
    POSITIVE LOGITS
     minimum
    0.06
     entitlement
    0.05
    æIJı
    0.05
    entos
    0.05
    ald
    0.05
    å¤ĸåĮħ
    0.05
     total
    0.05
    arno
    0.05
     devoted
    0.05
    номо
    0.05
    Activations Density 0.014%

    No Known Activations