© 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. 19883
    Prev
    Next
    INDEX
    Explanations

    section identifiers

    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
    earing
    -0.06
    å®ī举
    -0.06
    اÙĨÙĩ
    -0.05
    inan
    -0.05
     Eaton
    -0.05
     pá
    -0.05
    нее
    -0.05
     prem
    -0.05
    å®ľå®¶
    -0.05
    kli
    -0.05
    POSITIVE LOGITS
    çıį
    0.06
     scad
    0.06
    jf
    0.06
    urat
    0.06
    quat
    0.05
    perm
    0.05
    æ§
    0.05
    æ··
    0.05
    è¿Ļå°ıåŃIJ
    0.05
    cket
    0.05
    Activations Density 0.045%

    No Known Activations