© 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. 22244
    Prev
    Next
    INDEX
    Explanations

    force and forces

    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
    ampie
    -0.08
    emor
    -0.07
     nues
    -0.06
    wards
    -0.06
    åıijå¸ĥåħ¬åijĬ
    -0.06
     Newly
    -0.06
    arrass
    -0.06
    anlage
    -0.06
    dd
    -0.06
    ä½İä½į
    -0.06
    POSITIVE LOGITS
    æ±ĩ
    0.06
    urable
    0.05
     Fleming
    0.05
    pend
    0.05
     translated
    0.05
    鼨
    0.05
     piercing
    0.05
    cardo
    0.05
    عاÙħ
    0.05
    é¢Ŀ
    0.05
    Activations Density 0.012%

    No Known Activations