© 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. 21726
    Prev
    Next
    INDEX
    Explanations

    Newton and Newtown references

    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
    eness
    -0.06
    agus
    -0.06
    aturing
    -0.06
    bage
    -0.06
    ugging
    -0.05
    olas
    -0.05
    коном
    -0.05
    żyn
    -0.05
    Increasing
    -0.05
    çĶ¨åħ·
    -0.05
    POSITIVE LOGITS
    soever
    0.07
    -fluid
    0.06
    swith
    0.06
    ÑģÑı
    0.06
    alth
    0.06
     заказÑĭ
    0.06
    atl
    0.06
    ä¾£
    0.05
     fluid
    0.05
    dy
    0.05
    Activations Density 0.003%

    No Known Activations