© 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. 17763
    Prev
    Next
    INDEX
    Explanations

    description or attributes

    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
    der
    -0.06
    ards
    -0.05
    ech
    -0.05
    reve
    -0.05
     erlä
    -0.05
     prov
    -0.05
    ill
    -0.05
    ayers
    -0.05
    ral
    -0.05
    éĹ¹
    -0.05
    POSITIVE LOGITS
    losed
    0.06
    åĪ°åħ¶ä»ĸ
    0.06
    æīĢæ¶īåıĬ
    0.06
    leiter
    0.06
    ukai
    0.06
    åĪ°é«ĺ
    0.06
    poÅĽred
    0.06
    legant
    0.06
    bland
    0.06
    çļĦè¿Ļç§į
    0.06
    Activations Density 0.024%

    No Known Activations