© 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. 21453
    Prev
    Next
    INDEX
    Explanations

    Claude and common names

    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
    road
    -0.07
    è¾IJå°Ħ
    -0.06
    ÙĬÙħØ©
    -0.06
    åį³åĪ°
    -0.06
    adini
    -0.06
    ׳×ķת
    -0.06
    ä¸įè¾ŀ
    -0.06
    ستاÙĨÛĮ
    -0.06
     gedacht
    -0.06
    å¤Ħ
    -0.06
    POSITIVE LOGITS
    ì°°
    0.05
    verg
    0.05
    rieve
    0.05
    æĬ¼
    0.05
    оÑģ
    0.05
    aire
    0.05
     privately
    0.05
    ipel
    0.05
    ±
    0.05
    ÙĤد
    0.05
    Activations Density 0.001%

    No Known Activations