© 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. 18528
    Prev
    Next
    INDEX
    Explanations

    like discourse marker

    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
    IPC
    -0.05
    ç¤İ
    -0.05
    flux
    -0.05
    波士
    -0.05
    zas
    -0.05
    jde
    -0.05
    osting
    -0.05
    ç´Ľ
    -0.05
     pasaran
    -0.05
     biá»ĥn
    -0.05
    POSITIVE LOGITS
    ÙĦÙĥ
    0.06
    æ¯Ķä½ł
    0.06
    cede
    0.06
    cala
    0.06
    ced
    0.06
    ener
    0.06
    еÑģÑĤвен
    0.06
    çĹ
    0.06
    Ø©
    0.05
    ä¸įä»ħå¦ĤæѤ
    0.05
    Activations Density 0.012%

    No Known Activations