© 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. 22111
    Prev
    Next
    INDEX
    Explanations

    numeric comparison or assignment

    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
     boj
    -0.06
    ofs
    -0.06
    zd
    -0.06
     gue
    -0.05
    forc
    -0.05
    culp
    -0.05
    exter
    -0.05
    ews
    -0.05
    fone
    -0.05
    emap
    -0.05
    POSITIVE LOGITS
    å¥½ä¸ľè¥¿
    0.06
     NSF
    0.05
    é
    0.05
    ML
    0.05
    intang
    0.05
    ed
    0.05
    ,double
    0.05
    ac
    0.05
    i
    0.05
    гоÑĤ
    0.05
    Activations Density 0.002%

    No Known Activations