© 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. 19401
    Prev
    Next
    INDEX
    Explanations

    `View` related programming constructs

    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
    æ»ĵ
    -0.06
    acce
    -0.06
    å±ij
    -0.05
    ietet
    -0.05
    ibles
    -0.05
    ãĥĴãĥ³ãĥĪ
    -0.05
     Rules
    -0.05
     поза
    -0.05
     Hunde
    -0.05
    游æĪıè§ĦåĪĻ
    -0.05
    POSITIVE LOGITS
    instead
    0.06
     objective
    0.06
     instead
    0.06
    ustr
    0.06
    客è§Ĥ
    0.05
    ÑīноÑģÑĤÑĮ
    0.05
    为己任
    0.05
     merit
    0.05
    éĢ
    0.05
    objective
    0.05
    Activations Density 0.002%

    No Known Activations