© 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. 17538
    Prev
    Next
    INDEX
    Explanations

    will or 'll followed by a verb

    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
    ãi
    -0.05
     Oblig
    -0.05
    uce
    -0.05
    ingham
    -0.05
    qe
    -0.05
     bạc
    -0.05
    éĢŁéĢĴ
    -0.05
     frustr
    -0.05
    age
    -0.05
    phans
    -0.05
    POSITIVE LOGITS
    adb
    0.07
    æĺ¯ä¸įæĺ¯å¾Ī
    0.06
    ترض
    0.06
    arczy
    0.06
    jal
    0.06
     Schla
    0.06
    olle
    0.06
    çĮľä½łåĸľæ¬¢
    0.06
    yra
    0.06
    taki
    0.06
    Activations Density 0.008%

    No Known Activations