© 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. 19796
    Prev
    Next
    INDEX
    Explanations

    words ending in ology

    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
    vij
    -0.06
    ä¹łè¿ijå¹³æĢ»ä¹¦è®°åħ³äºİ
    -0.06
    èĩ´çļĦ
    -0.06
    ãģªãģı
    -0.06
    gener
    -0.06
    tit
    -0.06
    åºĶå½ĵåIJij
    -0.06
     GENER
    -0.06
    isk
    -0.05
    iscos
    -0.05
    POSITIVE LOGITS
    ç³»
    0.06
     diety
    0.06
    ardia
    0.05
    urale
    0.05
    åĿıäºĭ
    0.05
     act
    0.05
    çĨŁ
    0.05
    éal
    0.05
    ux
    0.05
    ÑĢил
    0.05
    Activations Density 0.010%

    No Known Activations