© 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. 19169
    Prev
    Next
    INDEX
    Explanations

    `is` or `will` followed by a verb/participle

    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
    ieu
    -0.06
    åĭĴ
    -0.05
    itia
    -0.05
    ameron
    -0.05
    ÑģÑĤеÑĢа
    -0.05
    åĿĿ
    -0.05
    åħ·
    -0.05
    attle
    -0.05
    cardo
    -0.05
    IVES
    -0.05
    POSITIVE LOGITS
     either
    0.06
     supposedly
    0.06
     ideally
    0.06
     magari
    0.06
     "").
    0.06
     preferably
    0.06
     fak
    0.06
     ãģĵãģ¡ãĤīãģ¯
    0.06
     whatever
    0.06
    oga
    0.06
    Activations Density 0.244%

    No Known Activations